├── .dockerignore ├── .env_example ├── .github ├── CONTRIBUTING.md ├── ISSUE_TEMPLATE │ ├── bug_report.md │ └── feature_request.md ├── pull_request_template.md └── workflows │ ├── autotag.yml │ ├── docker-hub.yml │ ├── docker-publish.yml │ └── python-ci-tests.yml ├── .gitignore ├── CITATION.cff ├── CODE_OF_CONDUCT.md ├── ChangeLog.md ├── LICENSE ├── README.md ├── SECURITY.md ├── bin └── aip ├── data ├── .gitignore ├── .gitkeep ├── README.md ├── external │ ├── .gitkeep │ ├── do_not_block_these_ips_example.csv │ └── honeypots_public_ips_example.csv ├── interim │ └── .gitkeep ├── output │ └── .gitkeep ├── processed │ ├── .gitkeep │ └── prioritizers │ │ └── .gitkeep └── raw │ └── .gitkeep ├── etc ├── docker │ ├── Dockerfile │ ├── README.md │ └── entrypoint.sh └── ra.conf ├── images └── AIP_Diagram.png ├── lib └── aip │ ├── __init__.py │ ├── data │ ├── __init__.py │ ├── access.py │ └── functions.py │ ├── models │ ├── __init__.py │ ├── all.py │ ├── alpha.py │ ├── base.py │ ├── pareto.py │ └── prioritize.py │ └── utils │ ├── __init__.py │ ├── autoload.py │ ├── date_utils.py │ ├── generate_historical_blocklists.py │ ├── metrics.py │ └── run_models.py ├── requirements.txt └── tests ├── __init__.py └── test_lib_aip_utils_date_utils.py /.dockerignore: -------------------------------------------------------------------------------- 1 | venv/ 2 | env/ 3 | *.pyc 4 | *.pyo 5 | *.pyd 6 | __pycache__/ 7 | *.so 8 | *.egg 9 | *.egg-info/ 10 | .eggs/ 11 | .git/ 12 | .gitignore 13 | .DS_Store 14 | Thumbs.db 15 | *.log 16 | *.swp 17 | *.tmp 18 | build/ 19 | dist/ 20 | *.egg-info/ 21 | *.tar.gz 22 | *.zip 23 | node_modules/ 24 | .idea/ 25 | .vscode/ 26 | *.sublime-project 27 | *.sublime-workspace 28 | .dockerignore 29 | Dockerfile 30 | Dockerfile_MacM1 31 | images/ 32 | .github 33 | data/ 34 | tests/ 35 | -------------------------------------------------------------------------------- /.env_example: -------------------------------------------------------------------------------- 1 | # Environment variables go here, can be read by `python-dotenv` package: 2 | # 3 | # `src/script.py` 4 | # ---------------------------------------------------------------- 5 | # import dotenv 6 | # 7 | # project_dir = os.path.join(os.path.dirname(__file__), os.pardir) 8 | # dotenv_path = os.path.join(project_dir, '.env') 9 | # dotenv.load_dotenv(dotenv_path) 10 | # ---------------------------------------------------------------- 11 | # 12 | # DO NOT ADD THE REAL FILE TO VERSION CONTROL! 13 | 14 | ###### [config] ###### 15 | # Uncomment if you want raw data to cleaned after processed. 16 | # Note that if you mount the zeek output folder as a volume inside the docker 17 | # image instead of manually copy those directories to the data/raw folder, 18 | # and if you enable this option, then AIP WILL REMOVE YOUR ZEEK FILES!!! 19 | # Use with care, and only if the data/raw/ folder contains a copy of the files 20 | # to be processed. 21 | # True, TRUE, true, TrUe are equivalent 22 | #remove_raw_data = 'true' 23 | 24 | ###### [secret] ###### 25 | salt = 'mysecretsalt' 26 | 27 | # Magic string to copy external data to data/raw folder 28 | #magic = 'scp host:folder' 29 | magic = 'cp tests/mock_data/' 30 | 31 | # you can add here other data source secrets, like AWS keys and stuff 32 | -------------------------------------------------------------------------------- /.github/CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | # Contributing 2 | 3 | All contributions are welcomed. Thank you for taking the time to contribute to this project! 4 | 5 | ## What branch should you base your contribution on? 6 | 7 | Generally, base your contribution on the `development` branch. 8 | 9 | 10 | ## Naming Git branches for Pull Requests 11 | 12 | To keep the Git history clean and facilitate the revision of contributions we 13 | ask all branches to follow concise namings. These are the branch-naming patterns 14 | to follow when contributing: 15 | 16 | - bugfix-<>: pull request branch, contains one bugfix, 17 | - docs-<>: pull request branch, contains documentation work, 18 | - enhance-<>: pull request branch, contains one enhancement (not a new feature, but improvement nonetheless) 19 | - feature-<>: pull request branch, contains a new feature, 20 | - refactor-<>: pull request branch, contains code refactoring, 21 | 22 | 23 | ## Tests 24 | 25 | Our project uses `unittest` for testing. To ensure code quality and maintainability, please run all tests before opening a pull request. 26 | 27 | ## Creating a pull request 28 | 29 | Commits: 30 | - Commits should do one thing. Keep it simple. 31 | - Commit messages should be easily readable, in imperative style ("Fix memory leak in...", not "FixES mem...") 32 | 33 | Pull Requests: 34 | - If you have developed multiple features and/or bugfixes, create separate 35 | branches for each one of them, and request merges for each branch; 36 | - The cleaner your code/change/changeset is, the faster it will be merged. 37 | 38 | ## How can you contribute? 39 | 40 | * Report bugs 41 | * Suggest features and ideas 42 | * Pull requests with a solved GitHub issue and a new feature 43 | * Pull request with new content. 44 | 45 | 46 | ## Persistent Git Branches 47 | 48 | The following git branches are permanent in the repository: 49 | 50 | - `main`: contains the stable version of the repository. 51 | - `development`: contains the latest version of AIP with the latest changes. **All new features should be based on this branch.** 52 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/bug_report.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: Bug report 3 | about: Create a report to help us improve 4 | title: "[BUG]" 5 | labels: bug 6 | --- 7 | 8 | **Describe the bug** 9 | A clear and concise description of what the bug is. 10 | 11 | **To Reproduce** 12 | Steps to reproduce the behaviour if applicable. Be brief but make sure it can be reproduced. Bullet points are welcomed here. 13 | 1. Go to '...' 14 | 2. Click on '....' 15 | 3. Scroll down to '....' 16 | 4. See error 17 | 18 | **Expected behaviour** 19 | A clear and concise description of what you expected to happen. 20 | 21 | **Screenshots** 22 | If applicable, add screenshots to help explain your problem. 23 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature_request.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: Feature request 3 | about: Suggest an idea for this project 4 | title: "[FEAT]" 5 | labels: enhancement 6 | --- 7 | 8 | **Is your feature request related to a problem? Please describe.** 9 | A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] 10 | 11 | **Describe the solution you'd like** 12 | A clear and concise description of what you want to happen. 13 | 14 | **Describe alternatives you've considered** 15 | A clear and concise description of any alternative solutions or features you've considered. 16 | 17 | **Additional context** 18 | Add any other context or screenshots about the feature request here. 19 | -------------------------------------------------------------------------------- /.github/pull_request_template.md: -------------------------------------------------------------------------------- 1 | # Description 2 | 3 | Please include a summary of the changes and the related issue. Please also include relevant motivation and context. List any dependencies that are required for this change. 4 | 5 | Fixes # (issue) 6 | 7 | ## Type of change 8 | 9 | Please delete options that are not relevant. 10 | 11 | - [ ] Bug fix (non-breaking change which fixes an issue) 12 | - [ ] New feature (non-breaking change which adds functionality) 13 | - [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected) 14 | - [ ] This change requires a documentation update 15 | 16 | # How Has This Been Tested? 17 | 18 | Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration 19 | 20 | - [ ] Test A 21 | - [ ] Test B 22 | 23 | 24 | # Checklist 25 | 26 | - [ ] My code follows the style guidelines of this project 27 | - [ ] I have performed a self-review of my code 28 | - [ ] I have commented my code, particularly in hard-to-understand areas 29 | - [ ] My changes generate no new warnings 30 | 31 | # Changes to the documentation 32 | 33 | - [ ] I have made corresponding changes to the documentation 34 | -------------------------------------------------------------------------------- /.github/workflows/autotag.yml: -------------------------------------------------------------------------------- 1 | name: Auto Tag 2 | on: 3 | push: 4 | branches: 5 | - main 6 | jobs: 7 | Patch: 8 | runs-on: ubuntu-latest 9 | steps: 10 | - uses: actions/checkout@v2 11 | with: 12 | fetch-depth: '0' 13 | - name: Minor version for each merge 14 | id: taggerDryRun 15 | uses: anothrNick/github-tag-action@1.36.0 16 | env: 17 | GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} 18 | WITH_V: true 19 | DRY_RUN: true 20 | 21 | - name: echo new tag 22 | run: | 23 | echo "The next tag version will be: ${{ steps.taggerDryRun.outputs.new_tag }}" 24 | - name: echo tag 25 | run: | 26 | echo "The current tag is: ${{ steps.taggerDryRun.outputs.tag }}" 27 | - name: echo part 28 | run: | 29 | echo "The version increment was: ${{ steps.taggerDryRun.outputs.part }}" 30 | 31 | - name: Minor version for each merge 32 | id: taggerFinal 33 | uses: anothrNick/github-tag-action@1.36.0 34 | env: 35 | GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} 36 | WITH_V: true 37 | INITIAL_VERSION: 2.1.0 38 | DEFAULT_BUMP: minor 39 | -------------------------------------------------------------------------------- /.github/workflows/docker-hub.yml: -------------------------------------------------------------------------------- 1 | name: Docker Hub CI 2 | 3 | on: 4 | push: 5 | branches: [ main ] 6 | 7 | jobs: 8 | 9 | build: 10 | 11 | runs-on: ubuntu-latest 12 | 13 | steps: 14 | - uses: actions/checkout@v2 15 | 16 | - name: Docker Login 17 | uses: docker/login-action@v1 18 | with: 19 | username: ${{ secrets.DOCKER_USER }} 20 | password: ${{ secrets.DOCKER_PASSWORD }} 21 | 22 | - name: Docker meta 23 | id: docker_meta 24 | uses: docker/metadata-action@v4 25 | with: 26 | images: | 27 | ${{ secrets.DOCKER_USER }}/aip 28 | flavor: | 29 | latest=true 30 | tags: | 31 | type=sha 32 | - name: Build and push 33 | id: docker_build 34 | uses: docker/build-push-action@v2 35 | with: 36 | context: . 37 | file: etc/docker/Dockerfile 38 | tags: ${{ steps.docker_meta.outputs.tags }} 39 | labels: ${{ steps.docker_meta.outputs.labels }} 40 | push: true 41 | -------------------------------------------------------------------------------- /.github/workflows/docker-publish.yml: -------------------------------------------------------------------------------- 1 | name: Docker GHCR CI 2 | 3 | # This workflow uses actions that are not certified by GitHub. 4 | # They are provided by a third-party and are governed by 5 | # separate terms of service, privacy policy, and support 6 | # documentation. 7 | 8 | on: 9 | push: 10 | branches: [ "main" ] 11 | # Publish semver tags as releases. 12 | tags: [ 'v*.*.*' ] 13 | 14 | env: 15 | # Use docker.io for Docker Hub if empty 16 | REGISTRY: ghcr.io 17 | # github.repository as / 18 | IMAGE_NAME: stratosphereips/AIP 19 | 20 | 21 | jobs: 22 | build: 23 | 24 | runs-on: ubuntu-latest 25 | permissions: 26 | contents: read 27 | packages: write 28 | # This is used to complete the identity challenge 29 | # with sigstore/fulcio when running outside of PRs. 30 | id-token: write 31 | 32 | steps: 33 | - name: Checkout repository 34 | uses: actions/checkout@v3 35 | 36 | # Install the cosign tool except on PR 37 | # https://github.com/sigstore/cosign-installer 38 | - name: Install cosign 39 | if: github.event_name != 'pull_request' 40 | uses: sigstore/cosign-installer@v3.6.0 41 | with: 42 | cosign-release: 'v2.2.4' 43 | 44 | # Workaround: https://github.com/docker/build-push-action/issues/461 45 | - name: Setup Docker buildx 46 | uses: docker/setup-buildx-action@79abd3f86f79a9d68a23c75a09a9a85889262adf 47 | 48 | # Login against a Docker registry except on PR 49 | # https://github.com/docker/login-action 50 | - name: Log into registry ${{ env.REGISTRY }} 51 | if: github.event_name != 'pull_request' 52 | uses: docker/login-action@28218f9b04b4f3f62068d7b6ce6ca5b26e35336c 53 | with: 54 | registry: ${{ env.REGISTRY }} 55 | username: ${{ github.actor }} 56 | password: ${{ secrets.GITHUB_TOKEN }} 57 | 58 | # Extract metadata (tags, labels) for Docker 59 | # https://github.com/docker/metadata-action 60 | - name: Extract Docker metadata 61 | id: meta 62 | uses: docker/metadata-action@98669ae865ea3cffbcbaa878cf57c20bbf1c6c38 63 | with: 64 | images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }} 65 | 66 | # Build and push Docker image with Buildx (don't push on PR) 67 | # https://github.com/docker/build-push-action 68 | - name: Build and push Docker image 69 | id: build-and-push 70 | uses: docker/build-push-action@ac9327eae2b366085ac7f6a2d02df8aa8ead720a 71 | with: 72 | context: . 73 | file: etc/docker/Dockerfile 74 | push: ${{ github.event_name != 'pull_request' }} 75 | tags: ${{ steps.meta.outputs.tags }} 76 | labels: ${{ steps.meta.outputs.labels }} 77 | cache-from: type=gha 78 | cache-to: type=gha,mode=max 79 | 80 | # Sign the resulting Docker image digest except on PRs. 81 | # This will only write to the public Rekor transparency log when the Docker 82 | # repository is public to avoid leaking data. If you would like to publish 83 | # transparency data even for private images, pass --force to cosign below. 84 | # https://github.com/sigstore/cosign 85 | - name: Sign the published Docker image 86 | if: ${{ github.event_name != 'pull_request' }} 87 | env: 88 | COSIGN_EXPERIMENTAL: "true" 89 | # This step uses the identity token to provision an ephemeral certificate 90 | # against the sigstore community Fulcio instance. 91 | run: echo "${{ steps.meta.outputs.tags }}" | xargs -I {} cosign sign --yes {}@${{ steps.build-and-push.outputs.digest }} 92 | -------------------------------------------------------------------------------- /.github/workflows/python-ci-tests.yml: -------------------------------------------------------------------------------- 1 | name: Python CI Tests 2 | 3 | on: 4 | pull_request: 5 | branches: [main, development] 6 | 7 | jobs: 8 | test: 9 | runs-on: ubuntu-latest 10 | 11 | steps: 12 | - name: Check out the repository 13 | uses: actions/checkout@v3 14 | 15 | - name: Set up Python 16 | uses: actions/setup-python@v4 17 | with: 18 | python-version: '3.12' 19 | 20 | - name: Install dependencies 21 | run: | 22 | python -m pip install --upgrade pip 23 | pip install -r requirements.txt 24 | 25 | - name: Run Tests 26 | env: 27 | PYTHONDONTWRITEBYTECODE: 1 28 | run: python -m unittest discover -s tests -v 29 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .idea/ 2 | .env 3 | __pycache__/ 4 | *-run.sh 5 | venv/ 6 | *.venv/ 7 | *.swp 8 | 9 | -------------------------------------------------------------------------------- /CITATION.cff: -------------------------------------------------------------------------------- 1 | cff-version: 1.2.0 2 | title: "Stratosphere AIP: Attacker IP Prioritizer" 3 | message: 'If you use this software, please cite it as specified below.' 4 | url: "https://github.com/stratosphereips/AIP" 5 | type: software 6 | authors: 7 | - given-names: Thomas 8 | family-names: O'Hara 9 | - given-names: Joaquin 10 | family-names: Bogado 11 | orcid: 'https://orcid.org/0000-0001-9491-5698' 12 | - given-names: Veronica 13 | family-names: Valeros 14 | email: valerver@fel.cvut.cz 15 | affiliation: >- 16 | Stratosphere Laboratory, AIC, FEL, Czech 17 | Technical University in Prague 18 | orcid: 'https://orcid.org/0000-0003-2554-3231' 19 | - given-names: Sebastian 20 | family-names: Garcia 21 | email: garciseb@fel.cvut.cz 22 | affiliation: >- 23 | Stratosphere Laboratory, AIC, FEL, Czech 24 | Technical University in Prague 25 | orcid: 'https://orcid.org/0000-0001-6238-9910' -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- 1 | # Contributor Covenant Code of Conduct 2 | 3 | ## Our Pledge 4 | 5 | We as members, contributors, and leaders pledge to make participation in our 6 | community a harassment-free experience for everyone, regardless of age, body 7 | size, visible or invisible disability, ethnicity, sex characteristics, gender 8 | identity and expression, level of experience, education, socio-economic status, 9 | nationality, personal appearance, race, religion, or sexual identity 10 | and orientation. 11 | 12 | We pledge to act and interact in ways that contribute to an open, welcoming, 13 | diverse, inclusive, and healthy community. 14 | 15 | ## Our Standards 16 | 17 | Examples of behavior that contributes to a positive environment for our 18 | community include: 19 | 20 | * Demonstrating empathy and kindness toward other people 21 | * Being respectful of differing opinions, viewpoints, and experiences 22 | * Giving and gracefully accepting constructive feedback 23 | * Accepting responsibility and apologizing to those affected by our mistakes, 24 | and learning from the experience 25 | * Focusing on what is best not just for us as individuals, but for the 26 | overall community 27 | 28 | Examples of unacceptable behavior include: 29 | 30 | * The use of sexualized language or imagery, and sexual attention or 31 | advances of any kind 32 | * Trolling, insulting or derogatory comments, and personal or political attacks 33 | * Public or private harassment 34 | * Publishing others' private information, such as a physical or email 35 | address, without their explicit permission 36 | * Other conduct which could reasonably be considered inappropriate in a 37 | professional setting 38 | 39 | ## Enforcement Responsibilities 40 | 41 | Community leaders are responsible for clarifying and enforcing our standards of 42 | acceptable behavior and will take appropriate and fair corrective action in 43 | response to any behavior that they deem inappropriate, threatening, offensive, 44 | or harmful. 45 | 46 | Community leaders have the right and responsibility to remove, edit, or reject 47 | comments, commits, code, wiki edits, issues, and other contributions that are 48 | not aligned to this Code of Conduct, and will communicate reasons for moderation 49 | decisions when appropriate. 50 | 51 | ## Scope 52 | 53 | This Code of Conduct applies within all community spaces, and also applies when 54 | an individual is officially representing the community in public spaces. 55 | Examples of representing our community include using an official e-mail address, 56 | posting via an official social media account, or acting as an appointed 57 | representative at an online or offline event. 58 | 59 | ## Enforcement 60 | 61 | Instances of abusive, harassing, or otherwise unacceptable behavior may be 62 | reported to the community leaders responsible for enforcement at 63 | stratosphere+collectress@aic.fel.cvut.cz. 64 | All complaints will be reviewed and investigated promptly and fairly. 65 | 66 | All community leaders are obligated to respect the privacy and security of the 67 | reporter of any incident. 68 | 69 | ## Enforcement Guidelines 70 | 71 | Community leaders will follow these Community Impact Guidelines in determining 72 | the consequences for any action they deem in violation of this Code of Conduct: 73 | 74 | ### 1. Correction 75 | 76 | **Community Impact**: Use of inappropriate language or other behavior deemed 77 | unprofessional or unwelcome in the community. 78 | 79 | **Consequence**: A private, written warning from community leaders, providing 80 | clarity around the nature of the violation and an explanation of why the 81 | behavior was inappropriate. A public apology may be requested. 82 | 83 | ### 2. Warning 84 | 85 | **Community Impact**: A violation through a single incident or series 86 | of actions. 87 | 88 | **Consequence**: A warning with consequences for continued behavior. No 89 | interaction with the people involved, including unsolicited interaction with 90 | those enforcing the Code of Conduct, for a specified period of time. This 91 | includes avoiding interactions in community spaces as well as external channels 92 | like social media. Violating these terms may lead to a temporary or 93 | permanent ban. 94 | 95 | ### 3. Temporary Ban 96 | 97 | **Community Impact**: A serious violation of community standards, including 98 | sustained inappropriate behavior. 99 | 100 | **Consequence**: A temporary ban from any sort of interaction or public 101 | communication with the community for a specified period of time. No public or 102 | private interaction with the people involved, including unsolicited interaction 103 | with those enforcing the Code of Conduct, is allowed during this period. 104 | Violating these terms may lead to a permanent ban. 105 | 106 | ### 4. Permanent Ban 107 | 108 | **Community Impact**: Demonstrating a pattern of violation of community 109 | standards, including sustained inappropriate behavior, harassment of an 110 | individual, or aggression toward or disparagement of classes of individuals. 111 | 112 | **Consequence**: A permanent ban from any sort of public interaction within 113 | the community. 114 | 115 | ## Attribution 116 | 117 | This Code of Conduct is adapted from the [Contributor Covenant][homepage], 118 | version 2.0, available at 119 | https://www.contributor-covenant.org/version/2/0/code_of_conduct.html. 120 | 121 | Community Impact Guidelines were inspired by [Mozilla's code of conduct 122 | enforcement ladder](https://github.com/mozilla/diversity). 123 | 124 | [homepage]: https://www.contributor-covenant.org 125 | 126 | For answers to common questions about this code of conduct, see the FAQ at 127 | https://www.contributor-covenant.org/faq. Translations are available at 128 | https://www.contributor-covenant.org/translations. 129 | -------------------------------------------------------------------------------- /ChangeLog.md: -------------------------------------------------------------------------------- 1 | 2023/02/22 2 | - AIP Tool major reimplementation (Now Docker ready!) 3 | 4 | 11/12/2020 5 | V2.0.5 6 | - Added complete runtime logging system to main branch 7 | 8 | 09/12/2020 9 | V2.0.4 10 | - Added ASN checker for major organizations 11 | - Added tcp flag checker for import data 12 | - Create ASN branch for testing 13 | - Merged ASN branch with main 14 | 15 | 16/10/2020 16 | V2.0.3 17 | - Updated safelist for main branch 18 | 19 | 07/10/2020 20 | V2.0.2 21 | - Created branch V2.0.2 for testing 22 | - Fixed problem with parenthesis in the blocklist headers 23 | - Merged V2.0.2 with main 24 | 25 | 18/09/2020 26 | - Modified thresholds to shrink lists 27 | 28 | 17/09/2020 29 | - Moved the daily blocklists to a separate repository 30 | 31 | 15/09/2020 32 | - Created branch V3.0.0 for next major update 33 | 34 | 24/07/2020 35 | V2.0.1 36 | - Minor bug fixes 37 | 38 | 22/07/2020 39 | V2.0.0 40 | - Added a whitlist module, namely before using the main data file, program will check for IPs that should not be blocklisted 41 | - Added an auto-run script. 42 | - Changed the aging function so it keeps track og how much an IP needs to be reduced over time 43 | - Changed the threshold so that it is dynamic again 44 | - Fixed the cannot check safelist bug 45 | - Fixed the infinite loop bug for the prioritize new normalized rating function 46 | - Fixed other small bugs and improved code 47 | 48 | 07/05/2020 49 | V1.0.3 50 | - Updated README.md files 51 | - Updated AIP-How-To-Guide.md 52 | 53 | 28/04/2020 54 | V1.0.2 55 | - Fixed problem with calling modules incorrectly 56 | - Add ability to choose new instance, or running instance 57 | - Asks for input data file location 58 | - Checks if input directory exits 59 | - If directoy exist, creates needed folders in it, if it does not, asks if we wisd to continue, and creates it all 60 | - If not a new instance, simple asks where the old instance is. 61 | - IMPORTANT - There is a bug with updating an old instance! 62 | 63 | 24/04/2020 64 | V1.0.1 65 | - Separated eval module into another repo 66 | - Separated eval script and run AIP script 67 | - Worked on organization 68 | - Deleted unecessary functions in AIP.py 69 | - Removed old module files 70 | 71 | 02/04/2020 72 | V1.0.0 73 | - First major commit, via the correct methods 74 | - Removed old files that were no longer relevant 75 | - Committed Main and Run-AIP.sh, but not Eval and Total_Eval.sh because both still contain personal identifiers 76 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Attacker IP Prioritization (AIP) Tool 2 | [![Python CI Tests](https://github.com/stratosphereips/AIP/actions/workflows/python-ci-tests.yml/badge.svg?branch=development)](https://github.com/stratosphereips/AIP/actions/workflows/python-ci-tests.yml) 3 | [![CodeQL](https://github.com/stratosphereips/AIP/actions/workflows/github-code-scanning/codeql/badge.svg?branch=main)](https://github.com/stratosphereips/AIP/actions/workflows/github-code-scanning/codeql) 4 | [![Docker Hub CI](https://github.com/stratosphereips/AIP/actions/workflows/docker-hub.yml/badge.svg?branch=main)](https://github.com/stratosphereips/AIP/actions/workflows/docker-hub.yml) 5 | [![Docker GHCR CI](https://github.com/stratosphereips/AIP/actions/workflows/docker-publish.yml/badge.svg?branch=main)](https://github.com/stratosphereips/AIP/actions/workflows/docker-publish.yml) 6 | 7 | [![Docker Pulls](https://img.shields.io/docker/pulls/stratosphereips/aip?color=green)](https://hub.docker.com/r/stratosphereips/aip) 8 | [![GitHub issues](https://img.shields.io/github/issues/stratosphereips/AIP.svg?color=green)](https://github.com/stratosphereips/AIP/issues/) 9 | [![GitHub issues-closed](https://img.shields.io/github/issues-closed/stratosphereips/AIP.svg?color=green)](https://github.com/stratosphereips/AIP/issues?q=is%3Aissue+is%3Aclosed) 10 | [![GitHub open-pull-requests](https://img.shields.io/github/issues-pr-raw/stratosphereips/AIP?color=green&label=open%20PRs)](https://github.com/stratosphereips/AIP/pulls?q=is%3Aopen) 11 | [![GitHub pull-requests closed](https://img.shields.io/github/issues-pr-closed-raw/stratosphereips/AIP?color=green&label=closed%20PRs)](https://github.com/stratosphereips/AIP/pulls?q=is%3Aclosed) 12 | 13 | 14 | The Attacker IP Prioritization (AIP) is a tool to generate efficient and economic IP blocklists based on network traffic captured from honeypot networks. 15 | 16 | With the advent of 5G, IoT devices are directly connected often without firewall protection. Therefore we need blocklists that are small, efficient and economic. The AIP structure is shown below. 17 | 18 | ![Description of the AIP pipeline](images/AIP_Diagram.png "AIP Tool pipeline") 19 | 20 | ## AIP Models 21 | 22 | Each AIP model generates its own blocklist based on a specific criteria. The main models are: 23 | 24 | 1. **Prioritize New (PN)** 25 | - Focuses on IPs that are new or have not been seen frequently in previous data. 26 | - Useful to identify emerging attackers that are starting to target a network. 27 | 2. **Prioritize Consistent (PC)** 28 | - Focuses on IPs that have consistently attacked over time in previous data. 29 | - Useful to identify persistent attackers that continuously target a network. 30 | 3. **Alpha** 31 | - Provides a baseline identifying all attackers seen in the last 24 hours. 32 | - Useful to compare the effectiveness of other models. 33 | 4. **Alpha7** 34 | - Provides a baseline identifying all attackers seen in the last 7 days. 35 | - Useful to further compare the effectiveness of other models. 36 | 5. **Random Forest** 37 | - Focuses on IPs that are more likely to attack in the future. 38 | - A more experimental approach to increase blocklist efficiency. 39 | 40 | 41 | ## AIP Docker 42 | 43 | The best way to run AIP right now is using [Docker](etc/docker/README.md). 44 | 45 | ## Usage 46 | 47 | AIP will automatically attempt to run all the models using the available data. Assuming the Zeek data is located in its usual location: 48 | 49 | ```bash 50 | :~$ cd AIP 51 | :~$ docker run --rm -v /opt/zeek/logs/:/home/aip/AIP/data/raw:ro -v ${PWD}/data/:/home/aip/AIP/data/:rw --name aip stratosphereips/aip:latest bin/aip 52 | ``` 53 | 54 | To run AIP for a specific day: 55 | ```bash 56 | :~$ cd AIP 57 | :~$ docker run --rm -v /opt/zeek/logs/:/home/aip/AIP/data/raw:ro -v ${PWD}/data/:/home/aip/AIP/data/:rw --name aip stratosphereips/aip:latest bin/aip YYYY-MM-DD 58 | ``` 59 | 60 | ## License 61 | 62 | The Stratosphere AIP tool is licensed under [GNU General Public License v3.0](https://github.com/stratosphereips/AIP/blob/main/LICENSE). 63 | 64 | ## About 65 | This tool was developed at the Stratosphere Laboratory at the Czech Technical University in Prague. This is part of the [Stratosphere blocklist generation project](https://mcfp.felk.cvut.cz/publicDatasets/CTU-AIPP-BlackList/). 66 | 67 | This tool was originally born from the bachelor thesis of Thomas O'Hara, [The Attacker IP Prioritizer: An IoT Optimized Blacklisting Algorithm (2021)](https://dspace.cvut.cz/handle/10467/96722). 68 | -------------------------------------------------------------------------------- /SECURITY.md: -------------------------------------------------------------------------------- 1 | # Security Policy 2 | 3 | ## Reporting a Vulnerability 4 | 5 | Report security vulnerabilities to stratosphere+aip@aic.fel.cvut.cz. We are a small team. We will acknowledge your email as soon as we can. Report security vulnerabilities in third-party modules to the person or 6 | team maintaining the module. 7 | 8 | ## Disclosure Policy 9 | 10 | When our team receives a security bug report, we will take the following steps: 11 | 12 | * Confirm the problem and determine the impact. 13 | * Prepare a fix to the latest current version. 14 | -------------------------------------------------------------------------------- /bin/aip: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | """ 3 | AIP - Attacker IP Prioritizer 4 | 5 | Complete rewrite of AIP by Thomas O'Hara to make AIP easily extensible and docker 6 | compatible. 7 | 8 | Original code in 9 | https://github.com/the-o-man/AIP-Blacklist-Algorithm 10 | 11 | This program is free software: you can redistribute it and/or modify it under 12 | the terms of the GNU General Public License as published by the Free Software 13 | Foundation, either version 3 of the License, or (at your option) any later 14 | version. 15 | 16 | This program is distributed in the hope that it will be useful, but WITHOUT 17 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS 18 | FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. 19 | You should have received a copy of the GNU General Public License along with 20 | this program. If not, see . 21 | """ 22 | 23 | __authors__ = ["Joaquin Bogado "] 24 | __contact__ = "stratosphere@aic.fel.cvut.cz" 25 | __copyright__ = "Copyright 2022, Stratosphere Laboratory." 26 | __credits__ = ["Joaquín Bogado"] 27 | __deprecated__ = False 28 | __license__ = "GPLv3" 29 | __maintainer__ = "Joaquin Bogado" 30 | __version__ = "1.0.0" 31 | 32 | import argparse 33 | import logging 34 | from datetime import date 35 | from os import makedirs 36 | from os import path 37 | from aip.data.access import data_path 38 | from aip.models.alpha import Alpha 39 | from aip.models.prioritize import New 40 | from aip.models.prioritize import Consistent 41 | from aip.models.prioritize import RandomForest 42 | from aip.utils.date_utils import validate_and_convert_date 43 | 44 | 45 | def run_model(aip_model_name, aip_model, date_day): 46 | """ 47 | Run a given model with exception handling 48 | """ 49 | blocklist="" 50 | model_output_dir = path.join(data_path,'output',aip_model_name) 51 | # Make sure output directory is created 52 | if not path.exists(model_output_dir): 53 | makedirs(model_output_dir) 54 | 55 | try: 56 | blocklist = aip_model.run(date_day) 57 | blocklist.to_csv(path.join(model_output_dir, f'AIP-{aip_model_name}-{str(date_day)}.csv.gz'), index=False, compression='gzip') 58 | logging.info(f"{aip_model_name} model completed successfully.") 59 | except Exception as e: 60 | logging.error(f"Error running {aip_model_name} model: {e}", exc_info=True) 61 | 62 | 63 | def main(): 64 | parser = argparse.ArgumentParser(description='Attacker IP Prioritization (AIP) Tool') 65 | parser.add_argument('--date', type=str, help='The date for running the models in YYYY-MM-DD format. Defaults to today.', default=str(date.today())) 66 | parser.add_argument('--model', type=str, choices=['Alpha', 'Alpha7', 'Prioritize_New', 'Prioritize_Consistent', 'Random_Forest', 'all'], default='all', help='Select AIP model to run. Defaults to all.') 67 | parser.add_argument('-d', '--debug', required=False, help="Debugging mode.", action="store_const", dest="log_level", const=logging.DEBUG, default=logging.ERROR,) 68 | parser.add_argument('-v', '--verbose', required=False, help="Verbose mode", action="store_const", dest="log_level", const=logging.INFO,) 69 | 70 | args = parser.parse_args() 71 | 72 | # Set up logging 73 | log_fmt = '%(asctime)s - %(name)s - %(levelname)s - %(message)s' 74 | logging.basicConfig(level=args.log_level, format=log_fmt) 75 | 76 | # Validate input date 77 | run_date_day = validate_and_convert_date(args.date) 78 | 79 | # Run Alpha Model 80 | if args.model in ['Alpha', 'all']: 81 | run_model('Alpha', Alpha(), run_date_day) 82 | 83 | # Alpha 7 Model 84 | if args.model in ['Alpha7', 'all']: 85 | run_model('Alpha7', Alpha(lookback=7), run_date_day) 86 | 87 | # Prioritize New Model 88 | if args.model in ['Prioritize_New', 'all']: 89 | run_model('Prioritize_New', New(), run_date_day) 90 | 91 | # Prioritize Consistent Model 92 | if args.model in ['Prioritize_Consistent', 'all']: 93 | run_model('Prioritize_Consistent', Consistent(), run_date_day) 94 | 95 | # Prioritize Random Forest Model 96 | if args.model in ['Random_Forest', 'all']: 97 | run_model('Random_Forest', RandomForest(), run_date_day) 98 | 99 | if __name__ == '__main__': 100 | main() 101 | -------------------------------------------------------------------------------- /data/.gitignore: -------------------------------------------------------------------------------- 1 | external/* 2 | interim/* 3 | processed/* 4 | raw/* 5 | output/* 6 | -------------------------------------------------------------------------------- /data/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/data/.gitkeep -------------------------------------------------------------------------------- /data/README.md: -------------------------------------------------------------------------------- 1 | ## AIP folders description 2 | 3 | This folder structure follows the convention of the [cookiecutter datascience project](https://drivendata.github.io/cookiecutter-data-science/). It is described as follows: 4 | 5 | 6 | ├── data 7 | │ ├── external <- Data from third party sources. 8 | │ ├── interim <- Intermediate data that has been transformed. 9 | │ ├── processed <- The final, canonical data sets for modeling. 10 | │ ├── raw <- The original, immutable data dump. 11 | │ └── output <- The outputs of the models. Intended ONLY for bin/aip script to write in. 12 | 13 | Data is also inmutable, and thus no need to track it. Thus, data folder is in .gitignore file. 14 | -------------------------------------------------------------------------------- /data/external/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/data/external/.gitkeep -------------------------------------------------------------------------------- /data/external/do_not_block_these_ips_example.csv: -------------------------------------------------------------------------------- 1 | ip, 2 | 192.168.1.2, 3 | -------------------------------------------------------------------------------- /data/external/honeypots_public_ips_example.csv: -------------------------------------------------------------------------------- 1 | # List of IPs to look for to generate the attack files. 2 | public_ip,operation_start_date,operation_end_date 3 | 192.168.0.1,2020-01-01, 4 | -------------------------------------------------------------------------------- /data/interim/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/data/interim/.gitkeep -------------------------------------------------------------------------------- /data/output/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/data/output/.gitkeep -------------------------------------------------------------------------------- /data/processed/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/data/processed/.gitkeep -------------------------------------------------------------------------------- /data/processed/prioritizers/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/data/processed/prioritizers/.gitkeep -------------------------------------------------------------------------------- /data/raw/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/data/raw/.gitkeep -------------------------------------------------------------------------------- /etc/docker/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM python:3.12-slim AS builder 2 | 3 | # Create a non-root user 4 | ARG username=aip 5 | ARG uid=1000 6 | ARG gid=1000 7 | 8 | ENV USER=$username 9 | ENV UID=$uid 10 | ENV GID=$gid 11 | ENV HOME=/home/$USER 12 | 13 | RUN apt-get update && \ 14 | apt-get install -y python3-venv && \ 15 | rm -rf /var/lib/apt/lists/* 16 | 17 | RUN groupadd -g $GID $USER && \ 18 | useradd -m -u $UID -g $GID -s /bin/bash $USER 19 | 20 | # Switch to the non-root user 21 | USER $USER 22 | 23 | WORKDIR $HOME/AIP 24 | 25 | COPY requirements.txt . 26 | 27 | RUN python -m venv venv && \ 28 | ./venv/bin/pip install --no-cache-dir -r requirements.txt 29 | 30 | # Remove unnecessary files 31 | RUN find venv/ -type d -name '__pycache__' -exec rm -rf {} + 32 | RUN find venv/ -type d -name 'tests' -exec rm -rf {} + && \ 33 | find venv/ -type d -name '*.dist-info' -exec rm -rf {} + 34 | 35 | # Stage 2: Final stage 36 | FROM python:3.12-slim 37 | 38 | # Create a non-root user 39 | ARG username=aip 40 | ARG uid=1000 41 | ARG gid=1000 42 | 43 | ENV USER=$username 44 | ENV UID=$uid 45 | ENV GID=$gid 46 | ENV HOME=/home/$USER 47 | 48 | RUN groupadd -g $GID $USER && \ 49 | useradd -m -u $UID -g $GID -s /bin/bash $USER 50 | 51 | # Copy the entrypoint script 52 | COPY etc/docker/entrypoint.sh /usr/local/bin/ 53 | RUN chmod u+x /usr/local/bin/entrypoint.sh 54 | 55 | # Switch to the non-root user 56 | USER $USER 57 | 58 | WORKDIR $HOME/AIP 59 | 60 | # Copy venv from the builder stage 61 | COPY --from=builder $HOME/AIP/venv $HOME/AIP/venv 62 | 63 | # Copy aip files 64 | COPY --chown=$USER:$USER . . 65 | 66 | ENV PATH="$HOME/AIP/venv/bin:$PATH" 67 | 68 | ENTRYPOINT [ "/usr/local/bin/entrypoint.sh" ] 69 | -------------------------------------------------------------------------------- /etc/docker/README.md: -------------------------------------------------------------------------------- 1 | # Docker image for AIP 2 | 3 | AIP docker aims to help in development and deployment of AIP algorithms to newcommers. The code of the repository is mounted and available from inside the docker image. The source of the data and the output folder of AIP is also mounted as a data volume inside the data/ folder to decouple from where this data really is in the host machine, easying the AIP deployment. 4 | 5 | ## Build the image 6 | 7 | To build the image, you can run the following command. 8 | 9 | ```bash 10 | :~$ git clone https://github.com/stratosphereips/AIP.git 11 | :~$ cd AIP/ 12 | :~/AIP$ docker build --build-arg uid=1000 --file etc/docker/Dockerfile --tag aip:latest . 13 | ``` 14 | 15 | ## Prepare the data 16 | 17 | AIP needs raw network flow data to run. In this case, we assume you have Zeek logs in `/opt/zeek/logs`. 18 | 19 | Additionally, the following two files need to be edited and populated: 20 | - `data/external/do_not_block_these_ips_example.csv`: you want to add here IPs that should not appear on the AIP blocklists 21 | - `data/external/honeypots_public_ips_example.csv`: you want to add here the public IP of the honeypot or machine running Zeek 22 | 23 | First copy the files and then edit them: 24 | ```bash 25 | :~/AIP$ cp data/external/do_not_block_these_ips_example.csv data/external/do_not_block_these_ips.csv 26 | :~/AIP$ cp data/external/honeypots_public_ips_example.csv data/external/honeypots_public_ips.csv 27 | ``` 28 | 29 | ## Run the container 30 | 31 | To run the container of that image you can run the following command: 32 | 33 | ```bash 34 | :~/AIP$ docker run --rm -v /opt/zeek/logs/:/home/aip/AIP/data/raw:ro -v ${PWD}/data/:/home/aip/AIP/data/:rw --name aip aip:latest bin/aip 35 | ``` 36 | 37 | An example output is shown below: 38 | ``` 39 | 2024-10-23 13:02:36,513 - aip.data.access - DEBUG - Creating attacks for dates ['2024-10-22'] 40 | 2024-10-23 13:02:36,513 - aip.data.access - DEBUG - Making dataset from raw data for dates ['2024-10-22'] 41 | 2024-10-23 13:02:37,197 - aip.data.access - DEBUG - Writting file: /home/aip/AIP/data/interim/daily.conn.2024-10-22.csv.gz 42 | 2024-10-23 13:02:37,539 - aip.data.access - DEBUG - Writting file: /home/aip/AIP/data/processed/attacks.2024-10-22.csv.gz 43 | 2024-10-23 13:02:37,648 - aip.data.access - DEBUG - Creating attacks for dates ['2024-10-20', '2024-10-21'] 44 | ... 45 | ``` -------------------------------------------------------------------------------- /etc/docker/entrypoint.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash --login 2 | 3 | # Exit immediately if any command exits with a non-zero status 4 | set -e 5 | 6 | # Force the command prompt to display colors 7 | export force_color_prompt=yes 8 | 9 | # Activate the virtual environment 10 | source "$HOME/AIP/venv/bin/activate" 11 | 12 | 13 | # Execute any command passed to the container when run 14 | PYTHONPATH="$HOME/AIP/lib:$PYTHONPATH" python "$@" 15 | 16 | -------------------------------------------------------------------------------- /etc/ra.conf: -------------------------------------------------------------------------------- 1 | # 2 | # Argus Software 3 | # Copyright (c) 2000-2011 QoSient, LLC 4 | # All rights reserved. 5 | # 6 | # This program is free software; you can redistribute it and/or modify 7 | # it under the terms of the GNU General Public License as published by 8 | # the Free Software Foundation; either version 2, or (at your option) 9 | # any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU General Public License 17 | # along with this program; if not, write to the Free Software 18 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. 19 | # 20 | # 21 | # Ra.Print.All.Conf 22 | # 23 | # This ra rc file will print all the available fields for a given argus 24 | # record, seperated by a comma. 25 | 26 | #RA_FIELD_SPECIFIER= srcid seq stime ltime dur sstime sltime sdur dstime dltime ddur srng drng trans flgs avgdur stddev mindur maxdur saddr dir daddr proto sport dport sco dco stos dtos sdsb ddsb sttl dttl shops dhops sipid dipid pkts spkts dpkts bytes sbytes dbytes appbytes sappbytes dappbytes load sload dload rate srate drate loss sloss dloss ploss sploss dploss senc denc smac dmac smpls dmpls svlan dvlan svid dvid svpri dvpri sintpkt dintpkt sintpktact dintpktact sintpktidl dintpktidl sintpktmax sintpktmin dintpktmax dintpktmin sintpktactmax sintpktactmin dintpktactmax dintpktactmin sintpktidlmax sintpktidlmin dintpktidlmax dintpktidlmin jit sjit djit jitact sjitact djitact jitidl sjitidl djitidl state deldur delstime delltime dspkts ddpkts dsbytes ddbytes pdspkts pddpkts pdsbytes pddbytes suser:1500 duser:1500 tcpext swin dwin jdelay ldelay bins binnum stcpb dtcpb tcprtt synack ackdat inode smaxsz sminsz dmaxsz dminsz 27 | RA_PRINT_LABELS=0 28 | RA_FIELD_DELIMITER=',' 29 | RA_USEC_PRECISION=12 30 | RA_PRINT_NAMES=0 31 | RA_TIME_FORMAT="%Y-%m-%d %T.%f" 32 | RA_FIELD_SPECIFIER= stime saddr:27 daddr:27 dur sbytes spkts 33 | 34 | -------------------------------------------------------------------------------- /images/AIP_Diagram.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/images/AIP_Diagram.png -------------------------------------------------------------------------------- /lib/aip/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/lib/aip/__init__.py -------------------------------------------------------------------------------- /lib/aip/data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/lib/aip/data/__init__.py -------------------------------------------------------------------------------- /lib/aip/data/access.py: -------------------------------------------------------------------------------- 1 | """ 2 | AIP - Data access routines 3 | 4 | Rountines for data access. The 5 | get_attacks(start=None, end=None, dates=None, usecols=None) 6 | function should suffice to get the information of the attacks from the models. 7 | 8 | Models should invoque the function with a list of dates or a range (start, end). 9 | The function will return a list of Pandas DataFrames ordered by date. An example 10 | the data generated by create_attacks function (from the dataframes are readed) 11 | can be found in the tests/ folder of the project. 12 | 13 | This program is free software: you can redistribute it and/or modify it under 14 | the terms of the GNU General Public License as published by the Free Software 15 | Foundation, either version 3 of the License, or (at your option) any later 16 | version. 17 | 18 | This program is distributed in the hope that it will be useful, but WITHOUT 19 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS 20 | FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. 21 | You should have received a copy of the GNU General Public License along with 22 | this program. If not, see . 23 | """ 24 | 25 | __authors__ = ["Joaquin Bogado "] 26 | __contact__ = "stratosphere@aic.fel.cvut.cz" 27 | __copyright__ = "Copyright 2022, Stratosphere Laboratory." 28 | __credits__ = ["Joaquín Bogado"] 29 | __deprecated__ = False 30 | __license__ = "GPLv3" 31 | __maintainer__ = "Joaquin Bogado" 32 | __version__ = "0.0.1" 33 | 34 | import datetime as dt 35 | import logging 36 | import pandas as pd 37 | import numpy as np 38 | 39 | from aip.data.functions import scramble, read_zeek, getrawdata, removerawdata 40 | from joblib import Parallel, delayed 41 | from os import scandir, path 42 | from pathlib import Path 43 | 44 | project_dir = Path(__file__).resolve().parents[3] 45 | 46 | data_path = path.join(project_dir,'data') # Deprecated, do not use 47 | data_dir = path.join(project_dir,'data') 48 | 49 | def _get_honeypot_ips(for_date=None): 50 | ''' 51 | Filter those honeypots active due date for_date, if there are operation dates in the honeypot file. 52 | ''' 53 | logger = logging.getLogger(__name__) 54 | # Check if the file exists before attempting to read it 55 | honeypot_public_ips = path.join(project_dir, 'data', 'external', 'honeypots_public_ips.csv') 56 | 57 | if not path.exists(honeypot_public_ips): 58 | logger.error(f"File 'honeypot_public_ips.csv' does not exist. Raising error.") 59 | raise FileNotFoundError("Required file 'honeypots_public_ips.csv' does not exist.") 60 | 61 | honeypots = pd.read_csv(path.join(project_dir, 'data', 'external', 'honeypots_public_ips.csv'), comment='#') 62 | if for_date is not None: 63 | for_date = pd.to_datetime(for_date) 64 | if 'operation_start_date' in honeypots.keys(): 65 | honeypots['operation_start_date'] = pd.to_datetime(honeypots['operation_start_date']) 66 | if 'operation_end_date' in honeypots.keys(): 67 | honeypots['operation_end_date'] = honeypots['operation_end_date'].fillna(dt.date.today()) 68 | honeypots['operation_end_date'] = pd.to_datetime(honeypots['operation_end_date']) 69 | if ('operation_start_date' in honeypots.keys()) and 'operation_end_date' in honeypots.keys(): 70 | honeypots = honeypots[(for_date >= honeypots['operation_start_date']) & (for_date <= honeypots['operation_end_date'])] 71 | ips = honeypots.public_ip.values 72 | return ips 73 | 74 | def _process_zeek_files(zeek_files, date): 75 | ips = _get_honeypot_ips() 76 | daily = pd.DataFrame() 77 | for z in zeek_files: 78 | hourly = pd.DataFrame() 79 | zeekdata = read_zeek(z) 80 | for ip in ips: 81 | hourly = pd.concat([hourly, zeekdata[zeekdata['id.resp_h'] == ip]]) 82 | daily = pd.concat([daily, hourly]) 83 | return daily 84 | 85 | def _process_argus_files(argus_files, date): 86 | ips = _get_honeypot_ips() 87 | daily = pd.DataFrame() 88 | for a in argus_files: 89 | hourly = pd.DataFrame() 90 | argusdata = read_argus(a) 91 | for ip in ips: 92 | hourly = pd.concat([hourly, argusdata[argusdata['id.resp_h'] == ip]]) 93 | daily = pd.concat([daily, hourly]) 94 | return daily 95 | 96 | def _process_raw_files(date): 97 | ''' 98 | Create a dataset for the date string date in the data/interim folder 99 | THIS FUNCTION IS DESTRUCTIVE and will overwrite the datasets for the processed date if exists. 100 | ''' 101 | logger = logging.getLogger(__name__) 102 | # if data directory does not exist, execute the magic to get it 103 | if path.isdir(path.join(project_dir,'data','raw', date)) == False: 104 | logging.debug(f'Downloading data for {date}') 105 | getrawdata(date) 106 | # after this point, if directory does not exist, we can skip it. 107 | try: 108 | zeek_files = [x.path for x in scandir(path.join(project_dir,'data','raw', date)) if x.name.startswith('conn.')] 109 | except FileNotFoundError: 110 | logger.warning(f'Skipping {path.join(project_dir,"data","raw", date)}. Directory not exist.') 111 | return 112 | if len(list(zeek_files)) > 0: 113 | daily = _process_zeek_files(zeek_files, date) 114 | else: 115 | daily = pd.DataFrame() 116 | daily.to_csv(path.join(project_dir,'data','interim', f'daily.conn.{date}.csv.gz'), index=False, compression='gzip') 117 | logger.debug('Writting file: ' + path.join(project_dir,'data','interim', f'daily.conn.{date}.csv.gz')) 118 | #logger.debug('Removing raw data (not needed anymore): ' + path.join(project_dir,'data','raw', f'{date}')) 119 | #removerawdata(date) 120 | return 121 | 122 | def _extract_attacks(date): 123 | ''' 124 | Create a dataset for the date string date in the data/interim folder 125 | THIS FUNCTION IS DESTRUCTIVE and will overwrite the datasets for the processed date if exists. 126 | ''' 127 | logger = logging.getLogger(__name__) 128 | try: 129 | daily = pd.read_csv(path.join(project_dir,"data","interim", f'daily.conn.{date}.csv.gz')) 130 | daily['ts'] = pd.to_datetime(daily['ts']) 131 | daily['duration'] = daily.duration.replace('-',0).astype(float) 132 | except FileNotFoundError: 133 | logger.warning(f'Skipping {path.join(project_dir,"data","interim", f"daily.conn.{date}.csv.gz")}. File not exist.') 134 | # Generate an empty attacks file 135 | pd.DataFrame(columns=['orig', 'flows', 'duration', 'packets', 'bytes']).to_csv( 136 | path.join(project_dir,'data','processed', f'attacks.{date}.csv.gz'), index=False, compression='gzip') 137 | return 138 | except pd.errors.EmptyDataError: 139 | logger.warning(f'Skipping {path.join(project_dir,"data","interim", f"daily.conn.{date}.csv.gz")}. File is empty.') 140 | # Generate an empty attacks file 141 | pd.DataFrame(columns=['orig', 'flows', 'duration', 'packets', 'bytes']).to_csv( 142 | path.join(project_dir,'data','processed', f'attacks.{date}.csv.gz'), index=False, compression='gzip') 143 | return 144 | # Calculate the total attacks for each origin 145 | df = daily[['id.orig_h', 'duration', 'orig_pkts', 'orig_ip_bytes']].groupby(['id.orig_h']).sum() 146 | df.rename(columns={'duration':'duration', 'orig_pkts':'packets', 'orig_ip_bytes':'bytes'}, inplace=True) 147 | df['orig'] = df.index.values 148 | df['flows'] = daily.groupby(['id.orig_h']).count().ts.values 149 | df.reset_index(drop=True, inplace=True) 150 | logger.debug('Writting file: ' + path.join(project_dir,'data','processed', f'attacks.{date}.csv.gz')) 151 | df.to_csv(path.join(project_dir,'data','processed', f'attacks.{date}.csv.gz'), columns=['orig', 'flows', 'duration', 'packets', 'bytes'], index=False, compression='gzip') 152 | # logger.debug('Removing raw data (not needed anymore): ' + path.join(project_dir,'data','raw', f'{date}')) 153 | #removerawdata(date) 154 | return 155 | 156 | def process_zeek_files(dates=None): 157 | """ 158 | Creates the dataset or part of it 159 | """ 160 | logger = logging.getLogger(__name__) 161 | logger.debug(f'Making dataset from raw data for dates {dates}') 162 | if dates is None: 163 | dates = [] 164 | for x in scandir(path.join(project_dir, 'data', 'raw')): 165 | try: 166 | dt.datetime.strptime(x.name, '%Y-%m-%d') 167 | dates.append(x.name) 168 | except ValueError: 169 | pass 170 | Parallel(n_jobs=12, backend='multiprocessing')(delayed(_process_raw_files)(date) for date in dates) 171 | return 172 | 173 | def extract_attacks(dates=None): 174 | """ 175 | Creates the dataset or part of it 176 | """ 177 | logger = logging.getLogger(__name__) 178 | logger.debug(f'Creating attacks for dates {dates}') 179 | filesready = [x.name for x in scandir(path.join(project_dir, 'data', 'processed'))] 180 | datesnotready = [] 181 | for date in dates: 182 | if f'daily.conn.{date}.csv.gz' not in filesready: 183 | datesnotready.append(date) 184 | process_zeek_files(datesnotready) 185 | if dates is None: 186 | dates = [] 187 | for x in scandir(path.join(project_dir, 'data', 'interim')): 188 | try: 189 | dt.datetime.strptime(x.name, '%Y-%m-%d') 190 | dates.append(x.name) 191 | except ValueError: 192 | pass 193 | Parallel(n_jobs=12, backend='multiprocessing')(delayed(_extract_attacks)(date) for date in dates) 194 | return 195 | 196 | def get_attacks(start=None, end=None, dates=None, usecols=None): 197 | ''' 198 | Returns a DataFrame with the attacks between the dates start and end or the 199 | ones especified in the list dates. 200 | ''' 201 | if start is not None: 202 | dates = [str(x.date()) for x in pd.date_range(start, end)] 203 | 204 | filesready = [x.name for x in scandir(path.join(project_dir, 'data', 'processed'))] 205 | datesnotready = [] 206 | for date in dates: 207 | if f'attacks.{date}.csv.gz' not in filesready: 208 | datesnotready.append(str(date)) 209 | if len(datesnotready) > 0: 210 | extract_attacks(datesnotready) 211 | dfs = [pd.read_csv(path.join(project_dir, 'data', 'processed',f'attacks.{date}.csv.gz'), usecols=usecols, comment='#') 212 | for date in dates] 213 | return dfs 214 | 215 | if __name__ == '__main__': 216 | log_fmt = '%(asctime)s - %(name)s - %(levelname)s - %(message)s' 217 | #logging.basicConfig(level=logging.INFO, format=log_fmt) 218 | logging.basicConfig(level=logging.DEBUG, format=log_fmt) 219 | 220 | # find .env automagically by walking up directories until it's found, then 221 | # load up the .env entries as environment variables 222 | #load_dotenv(find_dotenv()) 223 | 224 | extract_attacks() 225 | 226 | -------------------------------------------------------------------------------- /lib/aip/data/functions.py: -------------------------------------------------------------------------------- 1 | import datetime as dt 2 | import gzip 3 | import hashlib 4 | import pandas as pd 5 | import shutil 6 | import subprocess, shlex 7 | import zeeklog2pandas as z2p 8 | 9 | from dotenv import dotenv_values 10 | from joblib import Parallel, delayed 11 | from os import makedirs, path, access, W_OK 12 | from pathlib import Path 13 | 14 | _project_dir = Path(__file__).resolve().parents[3] 15 | _config = { 16 | **dotenv_values(path.join(_project_dir, ".env")), # load sensitive variables 17 | } 18 | 19 | def read_zeek(path, **kwargs): 20 | try: 21 | df = z2p.read_zeek(path, **kwargs) 22 | if 'ts' in df.keys(): 23 | df['ts'] = pd.to_datetime(df.ts, unit='s') 24 | return df 25 | except: 26 | raise z2p.NotAZeekFile(path) 27 | 28 | def read_argus(path, **kwargs): 29 | from os import path as ospath 30 | if ospath.exists(path.path + '.csv'): 31 | df = pd.read_csv(path.path + '.csv') 32 | else: 33 | raconf = ospath.join(_project_dir, 'etc', 'ra.conf') 34 | result = subprocess.run(shlex.split(f'ra -F {raconf} -n -Z b -r {path.path}'), capture_output=True, text=True) 35 | open(path.path + '.csv', 'w').write(result.stdout) 36 | df = pd.read_csv(path.path + '.csv') 37 | df['StartTime'] = pd.to_datetime(df['StartTime']) 38 | df['Dur'] += 0.000000000001 39 | #subprocess.run(shlex.split(f'rm {path.name}.csv')) 40 | df.rename(columns={'StartTime':'ts', 'SrcAddr':'id.orig_h', 'DstAddr':'id.resp_h', 'Dur': 'duration', 'SrcBytes': 'orig_ip_bytes', 'SrcPkts': 'orig_pkts'}, inplace=True) 41 | return df 42 | 43 | def scramble(s): 44 | return hashlib.sha1(_config['salt'].encode() + s.encode()).hexdigest() 45 | 46 | def getrawdata(date): 47 | dt.datetime.strptime(date, '%Y-%m-%d') 48 | p = path.join(_project_dir,'data','raw', date) 49 | if access(p, W_OK): 50 | makedirs(p, exist_ok=True) 51 | commands = [shlex.split(_config['magic'] + f'{date}/conn.{x:02}* ' + p) for x in range(0,24)] 52 | Parallel(n_jobs=24, backend='threading')(delayed(subprocess.run)(c) for c in commands) 53 | 54 | def removerawdata(date, force=False): 55 | dt.datetime.strptime(date, '%Y-%m-%d') 56 | p = path.join(_project_dir,'data','raw', date) 57 | # Only delete raw data if explicitly allowed in the configuration file 58 | if (_config['remove_raw_data'].lower() == 'true') or force: 59 | shutil.rmtree(p) 60 | 61 | -------------------------------------------------------------------------------- /lib/aip/models/__init__.py: -------------------------------------------------------------------------------- 1 | from os import scandir, path 2 | from importlib import import_module 3 | from aip.utils.autoload import models 4 | 5 | s = scandir(path.abspath(path.dirname(__file__))) 6 | files = [] 7 | for f in s: 8 | if f.name.endswith('.py') and f.name != 'base.py' and f.name != '__init__.py': 9 | files.append(f) 10 | 11 | for f in files: 12 | import_module(f'aip.models.{f.name[:-3]}') 13 | -------------------------------------------------------------------------------- /lib/aip/models/all.py: -------------------------------------------------------------------------------- 1 | """ 2 | AIP - AllIPs Model 3 | 4 | This model filter the attackers of the previous X days. 5 | 6 | This program is free software: you can redistribute it and/or modify it under 7 | the terms of the GNU General Public License as published by the Free Software 8 | Foundation, either version 3 of the License, or (at your option) any later 9 | version. 10 | 11 | This program is distributed in the hope that it will be useful, but WITHOUT 12 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS 13 | FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. 14 | You should have received a copy of the GNU General Public License along with 15 | this program. If not, see . 16 | """ 17 | 18 | __authors__ = ["Joaquin Bogado "] 19 | __contact__ = "stratosphere@aic.fel.cvut.cz" 20 | __copyright__ = "Copyright 2022, Stratosphere Laboratory." 21 | __credits__ = ["Joaquín Bogado"] 22 | __deprecated__ = False 23 | __license__ = "GPLv3" 24 | __maintainer__ = "Joaquin Bogado" 25 | __version__ = "0.0.1" 26 | 27 | import pandas as pd 28 | 29 | from aip.models.base import BaseModel 30 | from aip.utils.autoload import register, models 31 | from aip.data.access import get_attacks 32 | from datetime import date, timedelta 33 | 34 | #__models__ = [] 35 | 36 | @register 37 | class AllIPs(BaseModel): 38 | def __init__(self, lookback=1): 39 | super().__init__() 40 | self.lookback = lookback 41 | 42 | def run(self, for_date=date.today()): 43 | start = '2020-07-05' 44 | end = str(for_date - timedelta(days=1)) 45 | # get all the attackers IPs 46 | attacks = get_attacks(start, end, usecols=['orig']) 47 | attacks = pd.concat(attacks) 48 | attacks = attacks.rename(columns={'orig':'ip'}) 49 | self.blocklist = attacks.drop_duplicates() 50 | self.sanitize() 51 | return self.blocklist 52 | 53 | -------------------------------------------------------------------------------- /lib/aip/models/alpha.py: -------------------------------------------------------------------------------- 1 | """ 2 | AIP - AlphaX Model 3 | 4 | This model filter the attackers of the previous X days. 5 | 6 | This program is free software: you can redistribute it and/or modify it under 7 | the terms of the GNU General Public License as published by the Free Software 8 | Foundation, either version 3 of the License, or (at your option) any later 9 | version. 10 | 11 | This program is distributed in the hope that it will be useful, but WITHOUT 12 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS 13 | FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. 14 | You should have received a copy of the GNU General Public License along with 15 | this program. If not, see . 16 | """ 17 | 18 | __authors__ = ["Joaquin Bogado "] 19 | __contact__ = "stratosphere@aic.fel.cvut.cz" 20 | __copyright__ = "Copyright 2022, Stratosphere Laboratory." 21 | __credits__ = ["Joaquín Bogado"] 22 | __deprecated__ = False 23 | __license__ = "GPLv3" 24 | __maintainer__ = "Joaquin Bogado" 25 | __version__ = "0.0.1" 26 | 27 | import pandas as pd 28 | 29 | from aip.models.base import BaseModel 30 | from aip.utils.autoload import register, models 31 | from aip.data.access import get_attacks 32 | from datetime import date, timedelta 33 | 34 | #__models__ = [] 35 | 36 | @register 37 | class Alpha(BaseModel): 38 | def __init__(self, lookback=1): 39 | super().__init__() 40 | self.lookback = lookback 41 | 42 | def run(self, for_date=date.today()): 43 | start = str(for_date - timedelta(days=self.lookback)) 44 | end = str(for_date - timedelta(days=1)) 45 | # get all the attackers IPs 46 | attacks = get_attacks(start, end, usecols=['orig']) 47 | attacks = pd.concat(attacks).drop_duplicates() 48 | attacks = attacks.rename(columns={'orig':'ip'}) 49 | self.blocklist = attacks 50 | self.sanitize() 51 | return self.blocklist 52 | 53 | @register 54 | class Alpha7(Alpha): 55 | def __init__(self, lookback=7): 56 | super().__init__() 57 | self.lookback = lookback 58 | -------------------------------------------------------------------------------- /lib/aip/models/base.py: -------------------------------------------------------------------------------- 1 | """ 2 | AIP - Base Model 3 | 4 | AIP Base Model. All the AIP models are subclases of the base model. 5 | 6 | This program is free software: you can redistribute it and/or modify it under 7 | the terms of the GNU General Public License as published by the Free Software 8 | Foundation, either version 3 of the License, or (at your option) any later 9 | version. 10 | 11 | This program is distributed in the hope that it will be useful, but WITHOUT 12 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS 13 | FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. 14 | You should have received a copy of the GNU General Public License along with 15 | this program. If not, see . 16 | """ 17 | 18 | __authors__ = ["Joaquin Bogado "] 19 | __contact__ = "stratosphere@aic.fel.cvut.cz" 20 | __copyright__ = "Copyright 2022, Stratosphere Laboratory." 21 | __credits__ = ["Joaquín Bogado"] 22 | __deprecated__ = False 23 | __license__ = "GPLv3" 24 | __maintainer__ = "Joaquin Bogado" 25 | __version__ = "0.0.1" 26 | 27 | import pandas as pd 28 | import logging 29 | 30 | from aip.data.access import data_dir 31 | from aip.utils.autoload import register, models 32 | from os import path 33 | 34 | # @register 35 | class BaseModel(): 36 | ''' 37 | Template class for AIP models 38 | ''' 39 | def __init__(self): 40 | # Set up the logger for the class 41 | self.logger = logging.getLogger(self.__class__.__name__) 42 | 43 | # Model initialization and configuration 44 | self.blocklist = pd.DataFrame() 45 | exclude_ips = path.join(data_dir, 'external', 'do_not_block_these_ips.csv') 46 | 47 | if path.exists(exclude_ips): 48 | self.donotblocklist = pd.read_csv(exclude_ips) 49 | else: 50 | # Warning: File 'do_not_block_these_ips.csv' does not exist. Initializing with empty DataFrame. 51 | self.logger.warning("File 'do_not_block_these_ips.csv' does not exist. Initializing with empty DataFrame.") 52 | self.donotblocklist = pd.DataFrame(columns=['ip']) 53 | 54 | def sanitize(self, blocklist=None): 55 | if blocklist is None: 56 | blocklist = self.blocklist 57 | blocklist = blocklist[blocklist.ip.isin(self.donotblocklist.ip) == False] 58 | self.blocklist = blocklist 59 | return blocklist 60 | 61 | def run(self): 62 | # Model execution. The result of the function should be a list of IPs to block. 63 | return self.blocklist 64 | 65 | -------------------------------------------------------------------------------- /lib/aip/models/pareto.py: -------------------------------------------------------------------------------- 1 | """ 2 | AIP - Pareto Model 3 | 4 | This model filter the attackers of the previous X days. 5 | 6 | This program is free software: you can redistribute it and/or modify it under 7 | the terms of the GNU General Public License as published by the Free Software 8 | Foundation, either version 3 of the License, or (at your option) any later 9 | version. 10 | 11 | This program is distributed in the hope that it will be useful, but WITHOUT 12 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS 13 | FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. 14 | You should have received a copy of the GNU General Public License along with 15 | this program. If not, see . 16 | """ 17 | 18 | __authors__ = ["Joaquin Bogado "] 19 | __contact__ = "stratosphere@aic.fel.cvut.cz" 20 | __copyright__ = "Copyright 2022, Stratosphere Laboratory." 21 | __credits__ = ["Joaquín Bogado"] 22 | __deprecated__ = False 23 | __license__ = "GPLv3" 24 | __maintainer__ = "Joaquin Bogado" 25 | __version__ = "0.0.1" 26 | 27 | import pandas as pd 28 | 29 | from aip.models.base import BaseModel 30 | from aip.utils.autoload import register, models 31 | from aip.data.access import get_attacks 32 | from datetime import date, timedelta 33 | 34 | 35 | def pareto8020(df, column, threshold=80): 36 | df = df.sort_values(by=column, ascending=False) 37 | cumsum = df[column].cumsum() * 100 / df[column].sum() 38 | return df[cumsum < threshold] 39 | 40 | @register 41 | class Pareto(BaseModel): 42 | def __init__(self, lookback=60): 43 | super().__init__() 44 | self.lookback = lookback 45 | 46 | def run(self, for_date=date.today()): 47 | start = str(for_date - timedelta(days=self.lookback)) 48 | end = str(for_date - timedelta(days=1)) 49 | column = 'flows' 50 | attacks = get_attacks(start, end, usecols=['orig', column]) 51 | attacks = pd.concat(attacks) 52 | attacks = pareto8020(attacks, column, threshold=80) 53 | attacks = pd.DataFrame(attacks.orig.unique(), columns=['ip']) 54 | self.blocklist = attacks 55 | self.sanitize() 56 | return self.blocklist 57 | 58 | -------------------------------------------------------------------------------- /lib/aip/models/prioritize.py: -------------------------------------------------------------------------------- 1 | """ 2 | AIP - Prioritize New/Consistent Algorithm 3 | 4 | This module prioritize the new/consistent attackers. 5 | 6 | This program is free software: you can redistribute it and/or modify it under 7 | the terms of the GNU General Public License as published by the Free Software 8 | Foundation, either version 3 of the License, or (at your option) any later 9 | version. 10 | 11 | This program is distributed in the hope that it will be useful, but WITHOUT 12 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS 13 | FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. 14 | You should have received a copy of the GNU General Public License along with 15 | this program. If not, see . 16 | """ 17 | 18 | __authors__ = ["Joaquin Bogado "] 19 | __contact__ = "stratosphere@aic.fel.cvut.cz" 20 | __copyright__ = "Copyright 2022, Stratosphere Laboratory." 21 | __credits__ = ["Joaquín Bogado"] 22 | __deprecated__ = False 23 | __license__ = "GPLv3" 24 | __maintainer__ = "Joaquin Bogado" 25 | __version__ = "0.0.1" 26 | 27 | 28 | import numpy as np 29 | import pandas as pd 30 | import time 31 | 32 | from aip.data.access import data_path, get_attacks 33 | from aip.models.base import BaseModel 34 | from aip.utils.autoload import register, models 35 | from datetime import date, datetime, timedelta 36 | from os import path 37 | from sklearn.ensemble import RandomForestClassifier 38 | 39 | 40 | def _add_knowledge(last_knowledge, day): 41 | print(f'DEBUG: PROCESSING DATE {day}') 42 | st_time = time.time() 43 | day = datetime.strptime(day, '%Y-%m-%d').date() 44 | p = path.join(data_path, 'processed', 'prioritizers') 45 | attacks = get_attacks(dates=[day]) 46 | df = attacks[0] 47 | if df.empty is True: 48 | last_knowledge.to_csv(path.join(p, f'knowledgebase-{day}-snapshot.gz'), 49 | columns=['orig', 'flows', 'duration','bytes', 'packets', 50 | 'mean_flows', 'mean_duration', 'mean_bytes', 'mean_packets', 51 | 'days_active', 'first_seen', 'last_seen'], 52 | index=False, compression='gzip') 53 | return last_knowledge 54 | df = df.rename(columns={"count": "flows"}) 55 | df.loc[:, 'first_seen'] = day 56 | df.loc[:, 'last_seen'] = day 57 | df.loc[:, 'days_active'] = 1 58 | df.loc[df['flows'] == 0, 'flows'] = 1 59 | last_knowledge = pd.concat([last_knowledge, df]) 60 | dates_min = last_knowledge.groupby('orig').first_seen.min() 61 | dates_max = last_knowledge.groupby('orig').last_seen.max() 62 | knowledge = last_knowledge.groupby('orig').sum(numeric_only=True) 63 | knowledge.loc[:,'first_seen'] = dates_min 64 | knowledge.loc[:,'last_seen'] = dates_max 65 | knowledge.loc[:,'mean_flows'] = knowledge['flows']/knowledge['days_active'] 66 | knowledge.loc[:,'mean_duration'] = knowledge['duration']/knowledge['flows'] 67 | knowledge.loc[:,'mean_bytes'] = knowledge['bytes']/knowledge['flows'] 68 | knowledge.loc[:,'mean_packets'] = knowledge['packets']/knowledge['flows'] 69 | knowledge.reset_index(inplace=True) 70 | knowledge.to_csv(path.join(p, f'knowledgebase-{day}-snapshot.gz'), 71 | columns=['orig', 'flows', 'duration','bytes', 'packets', 72 | 'mean_flows', 'mean_duration', 'mean_bytes', 'mean_packets', 73 | 'days_active', 'first_seen', 'last_seen'], 74 | index=False, compression='gzip') 75 | print(f'DEBUG: PROCESSED IN {(time.time() - st_time)/60} MINUTES.') 76 | return knowledge 77 | 78 | def _build_knowledge(start, end): 79 | dates = pd.date_range(start=start, end=end) 80 | last_knowledge = pd.DataFrame() 81 | for day in dates: 82 | last_knowledge = _add_knowledge(last_knowledge, str(day.date())) 83 | return last_knowledge 84 | 85 | 86 | class Knowledgebase(): 87 | ''' 88 | Object that represents the IP features database 89 | ''' 90 | 91 | def _check_date_param(self, day_unchk): 92 | if day_unchk == 'yesterday': 93 | day = str(date.today() - timedelta(days=1)) 94 | elif type(day_unchk) is str: 95 | # force is a date or throw and exception 96 | day = str(datetime.strptime(day_unchk, '%Y-%m-%d').date()) 97 | elif type(day_unchk) is date: 98 | day = str(day_unchk) 99 | return day 100 | 101 | def _load_knowledge_until(self, day): 102 | day = self._check_date_param(day) 103 | self.path = path.join(data_path, 104 | 'processed', 'prioritizers', f'knowledgebase-{day}-snapshot.gz') 105 | if not path.exists(self.path): 106 | self.build(end=datetime.strptime(day, '%Y-%m-%d').date()) 107 | self.knowledge = pd.read_csv(self.path) 108 | self.knowledge.loc[:, 'last_seen'] = pd.to_datetime(self.knowledge.last_seen) 109 | self.knowledge.loc[:, 'first_seen'] = pd.to_datetime(self.knowledge.first_seen) 110 | self.timeframe = (self.knowledge.last_seen.min(), self.knowledge.last_seen.max()) 111 | 112 | def __init__(self, load_until='yesterday'): 113 | day = self._check_date_param(load_until) 114 | self.path = path.join(data_path, 115 | 'processed', 'prioritizers', f'knowledgebase-{day}-snapshot.gz') 116 | self._load_knowledge_until(day) 117 | 118 | 119 | def build(self, start=date.today() - timedelta(days=2), end=date.today() - timedelta(days=1), force=False): 120 | if path.exists(self.path) and not force: 121 | print('Knowledge exists already. Use force=True to rebuild it') 122 | return 123 | # check if the snapshot for the start date exists 124 | # if not, all the snapshots must be created again 125 | p = path.join(data_path, 'processed', 'prioritizers') 126 | if not path.exists(path.join(p, f'knowledgebase-{str(start)}-snapshot.gz')): 127 | last_knowledge = _build_knowledge(start=start, end=end) 128 | else: 129 | days_ago = 1 130 | day = str(end - timedelta(days=days_ago)) 131 | while not path.exists(path.join(p, f'knowledgebase-{day}-snapshot.gz')): 132 | days_ago += 1 133 | day = str(end - timedelta(days=days_ago)) 134 | last_knowledge = pd.read_csv(path.join(p, f'knowledgebase-{day}-snapshot.gz')) 135 | last_knowledge.loc[:, 'first_seen'] = pd.to_datetime(last_knowledge.first_seen).dt.date 136 | last_knowledge.loc[:, 'last_seen'] = pd.to_datetime(last_knowledge.last_seen).dt.date 137 | while days_ago >= 1: 138 | days_ago -= 1 139 | day = str(end - timedelta(days=days_ago)) 140 | last_knowledge = _add_knowledge(last_knowledge, day) 141 | 142 | 143 | @register 144 | class Consistent(BaseModel): 145 | ''' 146 | Prioritize Consistent algorithm 147 | ''' 148 | 149 | def __init__(self): 150 | super().__init__() 151 | # Weights from Thomas' Thesis 152 | # nflows, conns, nbytes, npackets, 153 | # mean_flows, mean_conns, mean_bytes, mean_packets 154 | self.weights = [0.05, 0.05, 0.05, 0.05, 0.2, 0.2, 0.2, 0.2] 155 | self.score_threshold = 0.00002 156 | self.min_ip_number = 5000 157 | 158 | def _get_IP_scores(self): 159 | days_since_last_seen = np.array([x.days for x in (pd.to_datetime(date.today()) - self.db.knowledge.last_seen)]) 160 | features = self.db.knowledge[ 161 | ['flows', 'duration','bytes', 'packets', 'mean_flows', 162 | 'mean_duration', 'mean_bytes', 'mean_packets'] 163 | ].values 164 | normalized_features = np.zeros_like(features) 165 | for i in range(8): 166 | normalized_features[:,i] = (features[:,i] - features[:,i].min()) / (features[:,i].max() - features[:,i].min()) 167 | ipscores = normalized_features * self.weights 168 | ipscores = ipscores.sum(axis=1) 169 | days_since_last_seen = np.array([x.days for x in (pd.to_datetime(date.today()) - self.db.knowledge.last_seen)]) 170 | total_attack_time = np.array([x.days for x in (self.db.knowledge.last_seen - self.db.knowledge.first_seen)]) 171 | aging = 1 - (days_since_last_seen/(days_since_last_seen + total_attack_time)) 172 | ipscores *= aging 173 | return ipscores 174 | 175 | def run(self, for_date=date.today()): 176 | self.db = Knowledgebase(load_until=for_date - timedelta(days=1)) 177 | ipscores = self._get_IP_scores() 178 | df = pd.DataFrame() 179 | df['ip'] = self.db.knowledge['orig'].values 180 | df['score'] = ipscores 181 | df = df.sort_values(by='score', ascending=False) 182 | df = self.sanitize(df) 183 | if len(df[df.score > self.score_threshold]) < self.min_ip_number: 184 | df = df.iloc[:self.min_ip_number] 185 | else: 186 | df = df[df.score > self.score_threshold] 187 | return df 188 | 189 | 190 | @register 191 | class New(Consistent): 192 | ''' 193 | Prioritize New algorithm 194 | ''' 195 | 196 | def __init__(self): 197 | super().__init__() 198 | # Weights from Thomas' Thesis 199 | # nflows, conns, nbytes, npackets, 200 | # mean_flows, mean_conns, mean_bytes, mean_packets 201 | self.weights = [0.2, 0.2, 0.2, 0.2, 0.05, 0.05, 0.05, 0.05] 202 | self.score_threshold = 0.00001 203 | self.min_ip_number = 5000 204 | 205 | def _get_IP_scores(self): 206 | days_since_last_seen = np.array([x.days for x in (pd.to_datetime(date.today()) - self.db.knowledge.last_seen)]) 207 | features = self.db.knowledge[ 208 | ['flows', 'duration','bytes', 'packets', 'mean_flows', 209 | 'mean_duration', 'mean_bytes', 'mean_packets'] 210 | ].values 211 | normalized_features = np.zeros_like(features) 212 | for i in range(8): 213 | normalized_features[:,i] = (features[:,i] - features[:,i].min()) / (features[:,i].max() - features[:,i].min()) 214 | ipscores = normalized_features * self.weights 215 | ipscores = ipscores.sum(axis=1) 216 | aging = 2 / (2 + days_since_last_seen) 217 | ipscores *= aging 218 | return ipscores 219 | 220 | class RandomForest(BaseModel): 221 | ''' 222 | Prioritize Random Forest from Thomas O'Hara's thesis 223 | ''' 224 | 225 | def __init__(self): 226 | super().__init__() 227 | 228 | def _get_training_target_set(self, for_date=date.today()): 229 | 230 | target = Knowledgebase(load_until=for_date - timedelta(days=1)) 231 | target.attacks = get_attacks(dates=[(for_date - timedelta(days=1))])[-1] 232 | days_since_last_seen = np.array([x.days for x in (pd.to_datetime(for_date) - target.knowledge.last_seen)]) 233 | total_attack_time = np.array([x.days for x in (target.knowledge.last_seen - target.knowledge.first_seen)]) 234 | target.knowledge['last_attack_days'] = days_since_last_seen 235 | target.knowledge['first_attack_days'] = total_attack_time 236 | target.features = target.knowledge[target.knowledge['orig'].isin(target.attacks['orig'])] 237 | target.features = target.knowledge 238 | target.X = target.features.drop(columns=['orig', 'first_seen', 'last_seen']).values 239 | 240 | training = Knowledgebase(load_until=for_date - timedelta(days=2)) 241 | training.knowledge.loc[training.knowledge['flows'] == 0, 'flows'] = 1 242 | training.attacks = pd.concat(get_attacks(dates=[(for_date - timedelta(days=2))])) 243 | days_since_last_seen = np.array([x.days for x in (pd.to_datetime(for_date) - training.knowledge.last_seen)]) 244 | total_attack_time = np.array([x.days for x in (training.knowledge.last_seen - training.knowledge.first_seen)]) 245 | training.knowledge['last_attack_days'] = days_since_last_seen 246 | training.knowledge['first_attack_days'] = total_attack_time 247 | training.knowledge['target'] = training.knowledge['orig'].isin(target.attacks['orig']).values.astype(int) 248 | training.features = training.knowledge[training.knowledge['orig'].isin(training.attacks['orig'])] 249 | training.features = training.knowledge 250 | training.X = training.features.drop(columns=['orig', 'first_seen', 'last_seen', 'target']).values 251 | training.Y = training.features['target'].values 252 | return training, target 253 | 254 | def run(self, for_date=date.today()): 255 | training, target = self._get_training_target_set(for_date=for_date) 256 | clf = RandomForestClassifier(n_estimators=30) 257 | if (target.X.shape[0] > 0) and (training.X.shape[0] > 0): 258 | clf = clf.fit(training.X, training.Y) 259 | pred = clf.predict(target.X) 260 | df = target.features[pred.astype(bool)] 261 | df = df.rename(columns={'orig': 'ip'}) 262 | df = self.sanitize(df) 263 | return df[['ip']] 264 | else: 265 | df = pd.DataFrame(columns=[['ip']]) 266 | return df 267 | -------------------------------------------------------------------------------- /lib/aip/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/lib/aip/utils/__init__.py -------------------------------------------------------------------------------- /lib/aip/utils/autoload.py: -------------------------------------------------------------------------------- 1 | 2 | models = [] 3 | 4 | def register(cls): 5 | models.append(cls) 6 | return cls 7 | -------------------------------------------------------------------------------- /lib/aip/utils/date_utils.py: -------------------------------------------------------------------------------- 1 | import logging 2 | from datetime import datetime 3 | 4 | 5 | def validate_and_convert_date(date_str): 6 | """ 7 | Validates a date string in 'YYYY-MM-DD' format and converts it to a date object. 8 | """ 9 | try: 10 | dateobj = datetime.strptime(date_str, '%Y-%m-%d') 11 | return dateobj.date() 12 | except ValueError as e: 13 | logging.error(f"Invalid date format for '{date_str}', expected YYYY-MM-DD") 14 | raise ValueError(f"Invalid date format: {date_str}, expected YYYY-MM-DD") from e -------------------------------------------------------------------------------- /lib/aip/utils/generate_historical_blocklists.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | """ 3 | Tool to generate historical blocklists 4 | 5 | This program is free software: you can redistribute it and/or modify it under 6 | the terms of the GNU General Public License as published by the Free Software 7 | Foundation, either version 3 of the License, or (at your option) any later 8 | version. 9 | 10 | This program is distributed in the hope that it will be useful, but WITHOUT 11 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS 12 | FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. 13 | You should have received a copy of the GNU General Public License along with 14 | this program. If not, see . 15 | """ 16 | 17 | __authors__ = ["Joaquin Bogado "] 18 | __contact__ = "stratosphere@aic.fel.cvut.cz" 19 | __copyright__ = "Copyright 2022, Stratosphere Laboratory." 20 | __credits__ = ["Joaquín Bogado"] 21 | __deprecated__ = False 22 | __license__ = "GPLv3" 23 | __maintainer__ = "Joaquin Bogado" 24 | __version__ = "1.0.0" 25 | 26 | import logging 27 | import pandas as pd 28 | import time 29 | 30 | from aip.data.access import data_path, project_dir 31 | from aip.models.alpha import Alpha 32 | from aip.models.prioritize import New 33 | from aip.models.prioritize import Consistent 34 | from aip.models.prioritize import RandomForest 35 | from aip.models.prioritize import Knowledgebase 36 | from aip.models.pareto import Pareto 37 | from datetime import date, timedelta 38 | from joblib import Parallel, delayed 39 | from pathlib import Path 40 | from os import makedirs, path, scandir 41 | 42 | 43 | #project_dir = Path(__file__).resolve().parents[1] 44 | 45 | start = '2020-07-05' 46 | end = str(date.today()) 47 | 48 | if __name__ == '__main__': 49 | log_fmt = '%(asctime)s - %(name)s - %(levelname)s - %(message)s' 50 | #logging.basicConfig(level=logging.INFO, format=log_fmt) 51 | logging.basicConfig(level=logging.DEBUG, format=log_fmt) 52 | 53 | # not used in this stub but often useful for finding various files 54 | 55 | # load up the .env entries as environment variables 56 | #load_dotenv(find_dotenv()) 57 | 58 | def run_model_alpha(day): 59 | #Alpha Model 60 | output_dir = path.join(project_dir, 'data', 'output', 'alpha_model') 61 | if not path.exists(output_dir): 62 | makedirs(output_dir) 63 | alpha = Alpha() 64 | blocklist = alpha.run(for_date=day) 65 | blocklist = blocklist.rename(columns={'ip':'attacker'}) 66 | pd.DataFrame(blocklist, columns=['attacker']).to_csv(path.join(output_dir, f'alpha_{str(day)}.csv.gz'), index=False, compression='gzip') 67 | 68 | def run_model_alpha7(day): 69 | #Alpha 7 Model 70 | output_dir = path.join(project_dir, 'data', 'output', 'alpha7_model') 71 | if not path.exists(output_dir): 72 | makedirs(output_dir) 73 | alpha = Alpha(7) 74 | blocklist = alpha.run(for_date=day) 75 | blocklist = blocklist.rename(columns={'ip':'attacker'}) 76 | pd.DataFrame(blocklist, columns=['attacker']).to_csv(path.join(output_dir, f'alpha7_{str(day)}.csv.gz'), index=False, compression='gzip') 77 | 78 | def run_model_pn(day): 79 | # Prioritize New Model 80 | output_dir = path.join(data_path, 'output', 'prioritize_new') 81 | if not path.exists(output_dir): 82 | makedirs(output_dir) 83 | pn = New() 84 | blocklist = pn.run(for_date=day) 85 | blocklist.to_csv(path.join(output_dir, f'prioritize-new_{str(day)}.csv.gz'), index=False, compression='gzip') 86 | 87 | def run_model_pc(day): 88 | # Prioritize Consistent Model 89 | output_dir = path.join(data_path, 'output', 'prioritize_consistent') 90 | if not path.exists(output_dir): 91 | makedirs(output_dir) 92 | pc = Consistent() 93 | blocklist = pc.run(for_date=day) 94 | blocklist.to_csv(path.join(output_dir, f'prioritize-consistent_{str(day)}.csv.gz'), index=False, compression='gzip') 95 | 96 | def run_model_rf(day): 97 | # RandomForest Model 98 | output_dir = path.join(data_path, 'output', 'random_forest') 99 | if not path.exists(output_dir): 100 | makedirs(output_dir) 101 | rf = RandomForest() 102 | blocklist = rf.run(for_date=day) 103 | blocklist.to_csv(path.join(output_dir, f'rf_v1_30estimators_{str(day)}.csv.gz'), index=False, compression='gzip') 104 | 105 | def run_model_pareto(day): 106 | #Pareto Model 107 | output_dir = path.join(project_dir, 'data', 'output', 'pareto_model') 108 | if not path.exists(output_dir): 109 | makedirs(output_dir) 110 | pareto = Pareto() 111 | blocklist = pareto.run(for_date=day) 112 | blocklist = blocklist.rename(columns={'ip':'attacker'}) 113 | pd.DataFrame(blocklist, columns=['attacker']).to_csv(path.join(output_dir, f'pareto_{str(day)}.csv.gz'), index=False, compression='gzip') 114 | 115 | def run_models(day): 116 | print(day) 117 | #run_model_alpha(day) 118 | #run_model_pn(day) 119 | #run_model_pc(day) 120 | #run_model_rf(day) 121 | run_model_pareto(day) 122 | 123 | dates = [x.date() for x in (pd.date_range(start=start, end=end))] 124 | st_time = time.time() 125 | #print(f'Creating knowledgebase from {str(dates[0])} to the present') 126 | #k = Knowledgebase() 127 | # Need to build the knowledge outside the parallel loop 128 | # build() is not a reentrant function 129 | #k.build(start=dates[0], end=dates[-1]) 130 | #print(f'Knowledge created in {(time.time() - st_time)/60} minutes.') 131 | # for day in dates: 132 | # run_models(day) 133 | st_time = time.time() 134 | print('Running models') 135 | Parallel(n_jobs=16, backend='multiprocessing')(delayed(run_models)(day) for day in dates) 136 | print(f'Models run after {(time.time() - st_time)/60} minutes.') 137 | -------------------------------------------------------------------------------- /lib/aip/utils/metrics.py: -------------------------------------------------------------------------------- 1 | """ 2 | AIP - Metrics 3 | 4 | This module implements several metrics to measure the efficiency of the 5 | blocklists. 6 | 7 | This program is free software: you can redistribute it and/or modify it under 8 | the terms of the GNU General Public License as published by the Free Software 9 | Foundation, either version 3 of the License, or (at your option) any later 10 | version. 11 | 12 | This program is distributed in the hope that it will be useful, but WITHOUT 13 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS 14 | FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. 15 | You should have received a copy of the GNU General Public License along with 16 | this program. If not, see . 17 | """ 18 | 19 | __authors__ = ["Joaquin Bogado "] 20 | __contact__ = "stratosphere@aic.fel.cvut.cz" 21 | __copyright__ = "Copyright 2022, Stratosphere Laboratory." 22 | __credits__ = ["Joaquín Bogado"] 23 | __deprecated__ = False 24 | __license__ = "GPLv3" 25 | __maintainer__ = "Joaquin Bogado" 26 | __version__ = "0.0.1" 27 | 28 | import numpy as np 29 | import pandas as pd 30 | 31 | 32 | public_IPs = 3706452992 33 | 34 | def TPR(P, TP): 35 | # recall, sensitivity, hit rate 36 | return TP/P 37 | 38 | def TNR(N, TN): 39 | # specificity, selectivity 40 | return TN/N 41 | 42 | def PPV(TP, FP): 43 | # precision, 44 | return TP / (TP + FP) 45 | 46 | def NPV(TN, FN): 47 | return TN / (TN + FN) 48 | 49 | def FNR(P, FN): 50 | # miss rate 51 | return FN/P 52 | 53 | def FPR(N, FP): 54 | # fall-out 55 | return FP/N 56 | 57 | def FDR(TP, FP): 58 | # false discovery rate 59 | return FP / (FP + TP) 60 | 61 | def FOR(TN, FN): 62 | # false omission rate 63 | return FN / (FN + TN) 64 | 65 | def PLR(P, N, TP, FP): 66 | # positive likelihood ratio 67 | return TPR(P, TP)/FPR(N, FP) 68 | 69 | def NLR(P, N, TN, FN): 70 | # negative likelihood ratio 71 | return FNR(P, FN)/TNR(N, TN) 72 | 73 | def PT(P, N, TP, FP): 74 | # prevalence threshold 75 | return np.sqrt(FPR(N, FP))/(np.sqrt(TPR(P, TP))/np.sqrt(FPR(N, FP))) 76 | 77 | def CSI(TP, FP, FN): 78 | # threat score, critical success index 79 | return TP/(TP + FN + FP) 80 | 81 | def prevalence(P, N): 82 | return P / (P + N) 83 | 84 | def ACC(P, N, TP, TN): 85 | # accuracy 86 | return (TP + TN) / (P + N) 87 | 88 | def BA(P, N, TP, TN): 89 | # balanced accuracy 90 | return (TPR(P, TP) + TNR(N, TN))/2 91 | 92 | def F05_score(P, TP, FP): 93 | # the F0.5 score gives less weight to recall than to precision 94 | return 1.25*((PPV(TP, FP) * TPR(P, TP))/(.25*PPV(TP, FP)+TPR(P, TP))) 95 | 96 | def F1_score(TP, FP, FN): 97 | # the F1 score gives equal weight to recall than to precision 98 | # equal to 2*((PPV(TP, FP) * TPR(P, TP))/(PPV(TP, FP)+TPR(P, TP))) 99 | return (2*TP)/((2*TP) + FP + FN) 100 | 101 | def F2_score(P, TP, FP): 102 | # the F2 score gives more weight to recall than to precision 103 | return 5*((PPV(TP, FP) * TPR(P, TP))/(4*PPV(TP, FP)+TPR(P, TP))) 104 | 105 | def FM(P, TP, FP): 106 | # fowlkes-mallows index 107 | return np.sqrt(PPV(TP, FP) * TPR(P, TP)) 108 | 109 | def BM(P, N, TP, TN): 110 | # bookmarked informedness 111 | return TPR(P, TP) + TNR(N, TN) - 1 112 | 113 | def MK(TP, TN, FP, FN): 114 | # markdedness or Δp 115 | return PPV(TP, FP) + NPV(TN, FN) - 1 116 | 117 | def DOR(P, N, TP, TN, FP, FN): 118 | # diagnostics odds ratio 119 | try: 120 | return PLR(P, N, TP, FP) / NLR(P, N, TN, FN) 121 | except ZeroDivisionError: 122 | return -1 123 | 124 | def calculate_TPTNFPFN(attacklist, blocklist): 125 | TP = 0. 126 | TN = 0. 127 | FP = 0. 128 | FN = 0. 129 | attacklist = {k:0 for k in attacklist.ip.values} 130 | blocklist = {k:0 for k in blocklist.ip.values} 131 | for ip in blocklist: 132 | if ip in attacklist: 133 | TP += 1 134 | for ip in blocklist: 135 | if ip not in attacklist: 136 | FP += 1 137 | for ip in attacklist: 138 | if ip not in blocklist: 139 | FN += 1 140 | TN = float(public_IPs - len(attacklist) - FN - FP) 141 | return TP, TN, FP, FN 142 | 143 | def MCC(TP, TN, FP, FN): 144 | """ 145 | Calculates the Mathew's Correlation Coeficient 146 | """ 147 | if (TP+FP)*(TP+FN)*(TN+FP)*(TN+FN) == 0: 148 | return 0 149 | else: 150 | return ((TP*TN)-(FP*FN))/np.sqrt((TP+FP)*(TP+FN)*(TN+FP)*(TN+FN)) 151 | 152 | def calculate_nDCG(attacklist, blocklist): 153 | # Normalized Discounted Cumulative Gain 154 | attacklist = attacklist.sort_values(by='rank', ascending=False) 155 | df = pd.merge(attacklist, blocklist) 156 | df = df.sort_values(by='rank', ascending=False) 157 | DCGp = ((2**df['rank'])/np.log2(np.arange(1, len(df)+1)+1)).sum() 158 | IDCG = ((2**attacklist['rank'])/np.log2(np.arange(1, len(attacklist)+1)+1)).sum() 159 | try: 160 | return DCGp/IDCG 161 | except ZeroDivisionError: 162 | return 0 163 | 164 | def calculate_nCG(attacklist, blocklist): 165 | # normalized cumulative gain 166 | attacklist = attacklist.sort_values(by='rank', ascending=False) 167 | df = pd.merge(attacklist, blocklist) 168 | df = df.sort_values(by='rank', ascending=False) 169 | CG = df['rank'].sum() 170 | return CG 171 | 172 | #from sklearn.metrics import average_precision_score 173 | #def calculate_AUCPR(attacklist, blocklist): 174 | # y_true = blocklist.ip.isin(attacklist.ip).values 175 | # y_pred = 176 | 177 | def calculate_BG_score(attacklist, blocklist, FP1_percent=0.0): 178 | FP1_impact = 10**6 179 | FP2_impact = 10 180 | TP, TN, FP, FN= calculate_TPTNFPFN(attacklist, blocklist) 181 | fpw = 1/(public_IPs - len(attacklist)) 182 | CG = calculate_nCG(attacklist, blocklist) 183 | FP1 = int((FP*FP1_percent)/100) 184 | DG = ((FP - FP1) * fpw * FP2_impact) + (FP1 * fpw * FP1_impact) 185 | return CG - DG 186 | 187 | #def calculate_BG_score(attacklist, blocklist, FP1_percent=0.0): 188 | # #FP1_impact = 1#0**6 189 | # #FP2_impact = 1#0 190 | # TP, TN, FP, FN = calculate_TPTNFPFN(attacklist, blocklist) 191 | # #fp1w = 1/whitelisted_ips 192 | # #fp2w = 1/(n_pub_ips - whitelisted_ips - len(attacks)) 193 | # #fpw = 1/(n_pub_ips - len(attacks)) 194 | # fprank = list(attacklist['rank'].values) 195 | # fprank.sort() 196 | # CG = calculate_nCG(attacklist, blocklist) 197 | # DG = np.sum(fprank[:int(min(len(fprank), FP))] + [fprank[-1]]*int(max(0, FP - len(fprank)))) 198 | # return CG - DG 199 | 200 | def calculate_coverage(attacklist, blocklist): 201 | df = pd.merge(attacklist, blocklist) 202 | flows = df.flows.sum()/max(1, attacklist.flows.sum()) 203 | duration = df.duration.sum()/max(1, attacklist.duration.sum()) 204 | nbytes = df.bytes.sum()/max(1, attacklist.bytes.sum()) 205 | packets = df.packets.sum()/max(1, attacklist.packets.sum()) 206 | flows_ip = (df.flows/max(1, attacklist.flows.sum())).sum()/max(1, len(blocklist)) 207 | duration_ip = (df.duration/max(1, attacklist.duration.sum())).sum()/max(1, len(blocklist)) 208 | nbytes_ip = (df.bytes/max(1, attacklist.bytes.sum())).sum()/max(1, len(blocklist)) 209 | packets_ip = (df.packets/max(1, attacklist.packets.sum())).sum()/max(1, len(blocklist)) 210 | return flows*100, duration*100, nbytes*100, packets*100, flows_ip*100, duration_ip*100, nbytes_ip*100, packets_ip*100 211 | 212 | def get_rank(attacks): 213 | return (attacks.flows/attacks.flows.sum() + attacks.duration/attacks.duration.sum() + attacks.packets/attacks.packets.sum() + attacks['bytes']/attacks['bytes'].sum())/4 214 | 215 | metrics_columns = ['BL_len', 'P', 'N', 'TP', 'TN', 'FP', 'FN', 216 | 'coverage_flows', 'coverage_duration', 'coverage_packets', 'coverage_bytes', 217 | 'coverage_flows_ip', 'coverage_duration_ip', 'coverage_packets_ip', 'coverage_bytes_ip', 218 | 'true_positive_rate', 'true_negative_rate', 'positive_predictive_value','negative_predictive_value', 219 | 'false_negative_rate', 'false_positive_rate', 'false_discovery_rate', 'false_ommision_rate', 220 | 'positive_likelihood_ratio', 'negative_likelihood_ratio', 'critical_success_index', 221 | 'prevalence_threshold', 'prevalence', 'accuracy', 'balanced_accuracy', 222 | 'F0.5_score', 'F1_score', 'F2_score', 'fowlkes_mallows_index', 223 | 'bookmarked_informedness', 'markedness', 'matthews_correlation_coefficient','diagnostic_odds_ratio', 224 | 'normalized_cumulative_gain', 'normalized_discounted_cumulative_gain', 'bg_score'] 225 | 226 | def get_metrics(attacks, blocklist): 227 | if len(attacks) == 0: 228 | return [np.nan]*len(metrics_columns) 229 | if len(blocklist) == 0: 230 | return [np.nan]*len(metrics_columns) 231 | attacks['rank'] = get_rank(attacks) 232 | bl_len = len(blocklist) 233 | # contingency table 234 | P = len(attacks) 235 | N = public_IPs - P 236 | TP, TN, FP, FN = calculate_TPTNFPFN(attacks, blocklist) 237 | # coverage 238 | c_flows, c_duration, c_packets, c_bytes, c_flows_ip, c_duration_ip, c_packets_ip, c_bytes_ip = calculate_coverage(attacks, blocklist) 239 | ## contingency table based metrics 240 | # recall or true positive rate 241 | tpr = TPR(P, TP) 242 | # specificity, selectivity or true negative rate 243 | tnr = TNR(N, TN) 244 | # precision or positive predictive value 245 | precision = PPV(TP, FP) 246 | # negative predictive value 247 | npv = NPV(TN, FN) 248 | # miss rate or false negative rate 249 | fnr = FNR(P, FN) 250 | # fall out or false positive rate 251 | fpr = FPR(N, FP) 252 | # false discovery rate 253 | fdr = FDR(TP, FP) 254 | # false omission rate 255 | _for = FOR(TN, FN) 256 | # positive likelihood ratio 257 | plr = PLR(P, N, TP, FP) 258 | # negative likelihood ratio 259 | nlr = NLR(P, N, TN, FN) 260 | #critical_success_index 261 | csi = CSI(TP, FP, FN) 262 | # prevalence threshold 263 | pt = PT(P, N, TP, FP) 264 | # Prevalence 265 | pv = prevalence(P, N) 266 | # Accuracy 267 | acc = ACC(P, N, TP, TN) 268 | # Balanced accuracy 269 | ba = BA(P, N, TP, TN) 270 | # F0.5 score 271 | f05 = F05_score(P, TP, FP) 272 | # F1 score 273 | f1 = F1_score(TP, FP, FN) 274 | # F2 score 275 | f2 = F2_score(P, TP, FP) 276 | # fowlkes-mallows index 277 | fm = FM(P, TP, FP) 278 | # bookmarked informedness 279 | bm = BM(P, N, TP, TN) 280 | # markedness or Δp 281 | mk = MK(TP, TN, FP, FN) 282 | # diagnostics odds ratio 283 | dor = DOR(P, N, TP, TN, FP, FN) 284 | # matthews correlation coefficient 285 | mcc = MCC(TP, TN, FP, FN) 286 | # normalized cumulative gain 287 | ncg = calculate_nCG(attacks, blocklist) 288 | # normalized discounted cumulative gain (best case scenario) 289 | ndcg = calculate_nDCG(attacks, blocklist) 290 | # Bogado - Garcia score 291 | bg_score = calculate_BG_score(attacks, blocklist) 292 | 293 | return bl_len, P, N, TP, TN, FP, FN, c_flows, c_duration, c_packets, c_bytes, c_flows_ip, c_duration_ip, c_packets_ip, c_bytes_ip, tpr, tnr, precision, npv, fnr, fpr, fdr, _for, plr, nlr, csi, pt, pv, acc, ba, f05, f1, f2, fm, bm, mk, mcc, dor, ncg, ndcg, bg_score 294 | 295 | -------------------------------------------------------------------------------- /lib/aip/utils/run_models.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | """ 3 | Tool to generate historical blocklists 4 | 5 | This program is free software: you can redistribute it and/or modify it under 6 | the terms of the GNU General Public License as published by the Free Software 7 | Foundation, either version 3 of the License, or (at your option) any later 8 | version. 9 | 10 | This program is distributed in the hope that it will be useful, but WITHOUT 11 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS 12 | FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. 13 | You should have received a copy of the GNU General Public License along with 14 | this program. If not, see . 15 | """ 16 | 17 | __authors__ = ["Joaquin Bogado "] 18 | __contact__ = "stratosphere@aic.fel.cvut.cz" 19 | __copyright__ = "Copyright 2022, Stratosphere Laboratory." 20 | __credits__ = ["Joaquín Bogado"] 21 | __deprecated__ = False 22 | __license__ = "GPLv3" 23 | __maintainer__ = "Joaquin Bogado" 24 | __version__ = "1.0.0" 25 | 26 | import logging 27 | import numpy as np 28 | import pandas as pd 29 | import time 30 | 31 | from aip.data.access import data_dir, project_dir 32 | from aip import models 33 | from datetime import date, timedelta 34 | from joblib import Parallel, delayed 35 | from pathlib import Path 36 | from os import makedirs, path, scandir 37 | from aip.utils.metrics import get_metrics, metrics_columns 38 | 39 | 40 | #project_dir = Path(__file__).resolve().parents[1] 41 | 42 | start = '2022-01-03' 43 | end = '2022-01-31' 44 | 45 | n_jobs = 16 46 | 47 | if __name__ == '__main__': 48 | log_fmt = '%(asctime)s - %(name)s - %(levelname)s - %(message)s' 49 | #logging.basicConfig(level=logging.INFO, format=log_fmt) 50 | logging.basicConfig(level=logging.DEBUG, format=log_fmt) 51 | 52 | def run_model(day, model): 53 | output_dir = path.join(data_dir, 'output', str(model.__name__)) 54 | if not path.exists(output_dir): 55 | print(f'making dir {output_dir}') 56 | makedirs(output_dir) 57 | m = model() 58 | blocklist = m.run(for_date=day) 59 | try: 60 | blocklist = blocklist.rename(columns={'ip':'attacker'}) 61 | except TypeError: 62 | print(blocklist, day, model) 63 | raise TypeError 64 | pd.DataFrame(blocklist, columns=['attacker']).to_csv(path.join(output_dir, f'{model.__name__}_{str(day)}.csv.gz'), index=False, compression='gzip') 65 | 66 | def run_models(day): 67 | print(day, end='\r') 68 | for model in models.models: 69 | if model.__name__ not in excluded_models: 70 | #print(str(model.__name__)) 71 | run_model(day, model) 72 | 73 | def measure(attacks, day, modelname): 74 | blocklist = pd.read_csv(path.join(data_dir, 'output', f'{modelname}', f'{modelname}_{str(day)}.csv.gz')).rename(columns={'attacker':'ip'}) 75 | results = [f'{modelname}', f'{str(day)}'] 76 | results += get_metrics(attacks, blocklist) 77 | return results 78 | 79 | def calculate_metrics(day): 80 | print(day, end='\r') 81 | attacks = pd.read_csv(path.join(data_dir, 'processed', f'attacks.{str(day)}.csv.gz'), names=['ip', 'flows', 'duration', 'packets', 'bytes'], skiprows=1) 82 | results = [] 83 | for model in models.models: 84 | if model.__name__ not in excluded_models: 85 | results.append(measure(attacks, day, model.__name__)) 86 | #print(results) 87 | return results 88 | 89 | 90 | def make_metric_plots(): 91 | import matplotlib.pyplot as plt 92 | plt.rcParams["figure.figsize"] = (11,7) 93 | df = pd.read_csv(path.join(metrics_output_dir, f'model_metrics_results_{start}_{end}.csv.gz')) 94 | df['date'] = pd.to_datetime(df.date) 95 | for metric in metrics_columns: 96 | # one plot per metric including all the models. 97 | plt.subplots() 98 | for model in models.models: 99 | if model.__name__ not in excluded_models: 100 | selector = df.model == model.__name__ 101 | # WHY THE FUCK THE COLUMN TYPE OF THE DF ARE OBJECT?!?!?! 102 | plt.plot(df[selector]['date'], df[selector][metric].values.astype(float), label=model.__name__) 103 | plt.legend() 104 | plt.xlabel('date') 105 | plt.ylabel(metric) 106 | plt.title(metric) 107 | plt.grid() 108 | plt.savefig(path.join(metrics_output_dir, f'models_comparison_{metric}_{start}_{end}.png')) 109 | plt.close() 110 | 111 | dates = [x.date() for x in (pd.date_range(start=start, end=end))] 112 | st_time = time.time() 113 | print('Running models') 114 | excluded_models = ['RandomForest', 'Pareto', 'AllIPs'] 115 | Parallel(n_jobs=n_jobs, backend='multiprocessing')(delayed(run_models)(day) for day in dates) 116 | print() 117 | print(f'Models run after {(time.time() - st_time)/60} minutes.') 118 | 119 | st_time = time.time() 120 | print('Evaluating models') 121 | excluded_models = [] 122 | results = Parallel(n_jobs=n_jobs, backend='multiprocessing')(delayed(calculate_metrics)(day) for day in dates) 123 | print() 124 | print(f'Metrics taken after {(time.time() - st_time)/60} minutes.') 125 | results = np.array(results).reshape(-1, 2+len(metrics_columns)) 126 | metrics_output_dir = path.join(data_dir, 'output', 'metrics') 127 | if not path.exists(metrics_output_dir): 128 | print(f'making dir {metrics_output_dir}') 129 | makedirs(metrics_output_dir) 130 | df = pd.DataFrame(results, columns=['model', 'date'] + metrics_columns) 131 | df.to_csv(path.join(metrics_output_dir, f'model_metrics_results_{start}_{end}.csv.gz'), index=False, compression='gzip') 132 | 133 | make_plots = True 134 | excluded_models = [] 135 | if make_plots: 136 | make_metric_plots() 137 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | netaddr==0.8.0 2 | zeeklog2pandas 3 | scikit-learn 4 | joblib 5 | python-dotenv 6 | pandas 7 | -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stratosphereips/AIP/670b14ae87649112049fa270b651398881de14ef/tests/__init__.py -------------------------------------------------------------------------------- /tests/test_lib_aip_utils_date_utils.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | import logging 3 | from datetime import date 4 | from lib.aip.utils.date_utils import validate_and_convert_date 5 | 6 | 7 | # Suppress logging messages below CRITICAL level 8 | # to just get the result of the tests. 9 | logging.disable(logging.CRITICAL) 10 | 11 | class TestValidateAndConvertDate(unittest.TestCase): 12 | 13 | def test_valid_date(self): 14 | # Test with a valid date 15 | self.assertEqual(validate_and_convert_date("2024-10-27"), date(2024, 10, 27)) 16 | 17 | def test_empty_string(self): 18 | # Test with an empty string 19 | with self.assertRaises(ValueError): 20 | validate_and_convert_date("") 21 | 22 | def test_invalid_format(self): 23 | # Test with various invalid formats 24 | with self.assertRaises(ValueError): 25 | validate_and_convert_date("2024/10/27") 26 | 27 | with self.assertRaises(ValueError): 28 | validate_and_convert_date("27-10-2024") 29 | 30 | with self.assertRaises(ValueError): 31 | validate_and_convert_date("October 27, 2024") 32 | 33 | def test_nonexistent_date(self): 34 | # Test not existing date Feb 30th 35 | with self.assertRaises(ValueError): 36 | validate_and_convert_date("2024-02-30") 37 | 38 | # Test not existing month 13 39 | with self.assertRaises(ValueError): 40 | validate_and_convert_date("2024-13-01") 41 | 42 | def test_none_value(self): 43 | # Test with None as input 44 | with self.assertRaises(TypeError): 45 | validate_and_convert_date(None) 46 | 47 | def test_edge_case(self): 48 | # Test leap years 49 | self.assertEqual(validate_and_convert_date("2024-02-29"), date(2024, 2, 29)) 50 | 51 | if __name__ == '__main__': 52 | unittest.main() 53 | --------------------------------------------------------------------------------