└── README.md /README.md: -------------------------------------------------------------------------------- 1 | 2 | Papers on Trustworthy Anomaly Detection 3 | ================================= 4 | 5 | ## 1. Surveys on Trustworthy AI 6 | 7 | * (arxiv'21) **Trustworthy AI: A Computational Perspective**. *Liu Haochen, Yiqi Wang, Wenqi Fan, Xiaorui Liu, Yaxin Li, Shaili Jain, Yunhao Liu, Anil K. Jain, and Jiliang Tang*. [link](https://arxiv.org/abs/2107.06641) 8 | 9 | * (JAIR'21) **Socially Responsible AI Algorithms: Issues, Purposes, and Challenges**. *Cheng Lu, Kush R. Varshney, and Huan Liu*. [link](https://arxiv.org/abs/2101.02032) 10 | 11 | * (CSUR'21) **Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges**. *Ashmore Rob, Radu Calinescu, and Colin Paterson*. [link](https://dl.acm.org/doi/10.1145/3453444) 12 | 13 | * (arxiv'20) **Toward trustworthy AI development: mechanisms for supporting verifiable claims**. *Brundage Miles, Shahar Avin, Jasmine Wang, Haydn Belfield, Gretchen Krueger, Gillian Hadfield, Heidy Khlaaf et al.* [link](https://arxiv.org/abs/2004.07213) 14 | 15 | ## 2. Surveys on Anomaly Detection 16 | 17 | * (Proc. IEEE'21) **A Unifying Review of Deep and Shallow Anomaly Detection**. *Ruff Lukas, Jacob R. Kauffmann, Robert A. Vandermeulen, Grégoire Montavon, Wojciech Samek, Marius Kloft, Thomas G. Dietterich, and Klaus-Robert Müller*. [link](https://ieeexplore.ieee.org/document/9347460) 18 | 19 | * (CSUR'21) **Deep Learning for Anomaly Detection: A Review**. *Pang Guansong, Chunhua Shen, Longbing Cao, and Anton Van Den Hengel*. [link](https://dl.acm.org/doi/abs/10.1145/3439950) 20 | 21 | * (arxiv'21) **Generalized out-of-distribution detection: A survey**. *Yang, Jingkang, Kaiyang Zhou, Yixuan Li, and Ziwei Liu.* [link](https://arxiv.org/abs/2110.11334). 22 | 23 | * (arxiv'19) **Deep Learning for Anomaly Detection: A Survey**. *Chalapathy Raghavendra, and Sanjay Chawla*. [link](https://arxiv.org/abs/1901.03407) 24 | 25 | ### 2.1 Surveys on Specific Domains 26 | * (Euro S&P) **SoK: Explainable Machine Learning for Computer Security Applications**. *Azqa Nadeem, Daniël Vos, Clinton Cao, Luca Pajola, Simon Dieck, Robert Baumgartner, and Sicco Verwer.* [link](https://www.computer.org/csdl/proceedings-article/eurosp/2023/651200a221/1OFthl9pdEQ) 27 | 28 | * (arxiv'23) **SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability**. *Dipkamal Bhusal, Rosalyn Shin, Ajay Ashok Shewale, Monish Kumar Manikya Veerabhadran, Michael Clifford, Sara Rampazzi, and Nidhi Rastogi.* [link](https://arxiv.org/abs/2210.17376) 29 | 30 | * (CSUR'22) **Anomaly detection and failure root cause analysis in (micro) service-based cloud applications: A survey**. *Soldani Jacopo, and Antonio Brogi*. [link](https://dl.acm.org/doi/full/10.1145/3501297) 31 | 32 | * (CSUR'21) **A review on outlier/anomaly detection in time series data**. *Blázquez-García Ane, Angel Conde, Usue Mori, and Jose A. Lozano*. [link](https://dl.acm.org/doi/abs/10.1145/3444690) 33 | 34 | * (TKDE'21) **A Comprehensive Survey on Graph Anomaly Detection with Deep Learning**. *Ma Xiaoxiao, Jia Wu, Shan Xue, Jian Yang, Chuan Zhou, Quan Z. Sheng, Hui Xiong, and Leman Akoglu*. [link](https://ieeexplore.ieee.org/document/9565320) 35 | 36 | * (arxiv'20) **Anomaly Detection in Univariate Time-series: A Survey on the State-of-the-Art**. *Mohammad Braei, Sebastian Wagner*. [link](https://arxiv.org/abs/2004.00433) 37 | 38 | * (CSUR'20) **Anomaly detection in road traffic using visual surveillance: a survey**. *Santhosh Kelathodi Kumaran, Debi Prosad Dogra, and Partha Pratim Roy*. [link](https://dl.acm.org/doi/abs/10.1145/3417989) 39 | 40 | * (IoT J.'20) **Anomaly Detection for IoT Time-Series Data: A Survey**. *Cook Andrew A., Göksel Mısırlı, and Zhong Fan*. [link](https://ieeexplore.ieee.org/abstract/document/8926446) 41 | 42 | * (arxiv'19) **A Survey on GANs for Anomaly Detection**. *Di Mattia, Federico, Paolo Galeone, Michele De Simoni, and Emanuele Ghelfi*. [link](https://arxiv.org/abs/1906.11632) 43 | 44 | 45 | 46 | ## 3. Interpretable Anomaly Detection 47 | 48 | **Surveys** 49 | * (arxiv'23) **Explainable Anomaly Detection in Images and Videos: A Survey**. *Yizhou Wang, Dongliang Guo, Sheng Li, Octavia Camps, Yun Fu*. [link](https://arxiv.org/abs/2302.06670) 50 | 51 | * (VLDB J.'22) **A survey on outlier explanations**. *Panjei Egawati, Le Gruenwald, Eleazar Leal, Christopher Nguyen, and Shejuti Silvia.* [link](https://link.springer.com/article/10.1007/s00778-021-00721-1) 52 | 53 | * (TKDD'23) **A Survey on Explainable Anomaly Detection**. *Zhong Li, Yuxuan Zhu, Matthijs van Leeuwen* [link](https://dl.acm.org/doi/10.1145/3609333) 54 | 55 | **Approaches** 56 | * (KDD'22) **Framing Algorithmic Recourse for Anomaly Detection**. *Debanjan Datta, Feng Chen, Naren Ramakrishnan*. [link](https://dl.acm.org/doi/abs/10.1145/3534678.3539344) 57 | 58 | * (AAAI'21) **Anomaly attribution with likelihood compensation**. *Idé, Tsuyoshi, Amit Dhurandhar, Jiří Navrátil, Moninder Singh, and Naoki Abe*. [link](https://ojs.aaai.org/index.php/AAAI/article/view/16535) 59 | 60 | * (CCS'21) **DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications**. *Dongqi Han, Zhiliang Wang, Wenqi Chen, Ying Zhong, Su Wang, Han Zhang, Jiahai Yang, Xingang Shi, and Xia Yin.* [link](https://arxiv.org/abs/2109.11495) 61 | 62 | * (PVLDB'21) **Exathlon: a benchmark for explainable anomaly detection over time series**. *Vincent Jacob, Fei Song, Arnaud Stiegler, Bijan Rad, Yanlei Diao, and Nesime Tatbul*. [link](https://doi.org/10.14778/3476249.3476307) 63 | 64 | * (ICLR'21) **Explainable Deep One-Class Classification**. *Liznerski Philipp, Lukas Ruff, Robert A. Vandermeulen, Billy Joe Franks, Marius Kloft, and Klaus-Robert Müller.* [link](https://arxiv.org/abs/2007.01760) 65 | 66 | * (BigData'21) **InterpretableSAD: Interpretable Anomaly Detection in Sequential Log Data**. *Han Xiao, He Cheng, Depeng Xu, and Shuhan Yuan*. [link](https://ieeexplore.ieee.org/document/9671642) 67 | 68 | * (arxiv'21) **Explainable Deep Few-shot Anomaly Detection with Deviation Networks**. *Pang Guansong, Choubo Ding, Chunhua Shen, and Anton van den Hengel.* [link](https://arxiv.org/abs/2108.00462) 69 | 70 | * (ECCV'20) **Attention Guided Anomaly Localization in Images**. *Venkataramanan Shashanka, Kuan-Chuan Peng, Rajat Vikram Singh, and Abhijit Mahalanobis*. [link](https://arxiv.org/abs/1911.08616) 71 | 72 | * (ICML'20) **Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device Failure**. *John Sipple*. [link](https://arxiv.org/abs/2007.10088) 73 | 74 | * (PR'20) **Towards explaining anomalies: A deep Taylor decomposition of one-class models**. *Kauffmann Jacob, Klaus-Robert Müller, and Grégoire Montavon.* [link](https://www.sciencedirect.com/science/article/pii/S0031320320300054) 75 | 76 | * (CNS'19) **GEE: A Gradient-based Explainable Variational Autoencoder for Network Anomaly Detection**. *Nguyen Quoc Phong, Kar Wai Lim, Dinil Mon Divakaran, Kian Hsiang Low, and Mun Choon Chan.* [link](https://arxiv.org/abs/1903.06661) 77 | 78 | * (arxiv'19) **Explaining Anomalies Detected by Autoencoders Using SHAP**. *Antwarg, Liat, Ronnie Mindlin Miller, Bracha Shapira, and Lior Rokach.* [link](https://arxiv.org/abs/1903.02407) 79 | 80 | * (HPDC'18) **Recurrent Neural Network Attention Mechanisms for Interpretable System Log Anomaly Detection**. *Brown Andy, Aaron Tuor, Brian Hutchinson, and Nicole Nichols.* [link](https://arxiv.org/abs/1803.04967) 81 | 82 | * (ECML-PKDD'18) **Scalable and Interpretable One-class SVMs with Deep Learning and Random Fourier features**. *Nguyen Minh-Nghia, and Ngo Anh Vien*. [link](https://arxiv.org/abs/1804.04888) 83 | 84 | ## 4. Fair Anomaly Detection 85 | 86 | **Approaches** 87 | 88 | * (PAKDD'23) **Achieving Counterfactual Fairness for Anomaly Detection**. *Xiao Han, Lu Zhang, Yongkai Wu, and Shuhan Yuan.* [link](https://arxiv.org/abs/2303.02318) 89 | 90 | * (FAccT'21) **Towards Fair Deep Anomaly Detection**. *Zhang Hongjing, and Ian Davidson.* [link](https://dl.acm.org/doi/10.1145/3442188.3445878) 91 | 92 | * (AIES'21) **FairOD: Fairness-aware Outlier Detection**. *Shekhar Shubhranshu, Neil Shah, and Leman Akoglu.* [link](https://dl.acm.org/doi/10.1145/3461702.3462517) 93 | 94 | * (KDD'21) **Deep Clustering based Fair Outlier Detection**. *Song Hanyu, Peizhao Li, and Hongfu Liu.* [link](https://dl.acm.org/doi/abs/10.1145/3447548.3467225) 95 | 96 | * (ECAI'20) **A Framework for Determining the Fairness of Outlier Detection**. *Davidson Ian, and Selvan Suntiha Ravi.* [link](https://ebooks.iospress.nl/doi/10.3233/FAIA200379) 97 | 98 | * (WISE'20) **Fair Outlier Detection**. *Deepak P., and Savitha Sam Abraham.* [link](https://arxiv.org/abs/2005.09900) 99 | 100 | 101 | 102 | ## 5. Robust Anomaly Detection 103 | 104 | **Surveys** 105 | 106 | * (CSUR'22) **Adversarial Machine Learning Attacks and Defense Methods in the Cyber Security Domain**. *Rosenberg, Ishai, Asaf Shabtai, Yuval Elovici, and Lior Rokach*. [link](https://dl.acm.org/doi/abs/10.1145/3453158) 107 | 108 | * (arxiv'19) **The Threat of Adversarial Attacks on Machine Learning in Network Security -- A Survey**. *Ibitoye, Olakunle, Rana Abou-Khamis, Ashraf Matrawy, and M. Omair Shafiq*. [link](https://arxiv.org/abs/1911.02621) 109 | 110 | **Approaches** 111 | * (PAKDD'22) **IDSGAN: Generative Adversarial Networks for Attack Generation Against Intrusion Detection**. *Zilong Lin, Yong Shi, and Zhi Xue.* [link](https://link.springer.com/chapter/10.1007/978-3-031-05981-0_7) 112 | 113 | * (DTRAP'22) **Modeling Realistic Adversarial Attacks against Network Intrusion Detection Systems**. *Apruzzese, Giovanni, Mauro Andreolini, Luca Ferretti, Mirco Marchetti, and Michele Colajanni.* [link](https://dl.acm.org/doi/10.1145/3469659) 114 | 115 | * (arxiv'21) **Adversarially Robust One-class Novelty Detection**. *Lo, Shao-Yuan, Poojan Oza, and Vishal M. Patel.* [link](https://arxiv.org/abs/2108.11168) 116 | 117 | * (IJCAI'21) **Robustness of Autoencoders for Anomaly Detection Under Adversarial Impact**. *Goodge, Adam, Bryan Hooi, See-Kiong Ng, and Wee Siong Ng.* [link](https://www.ijcai.org/proceedings/2020/173) 118 | 119 | * (TrustCom'21) **An Approach for Poisoning Attacks Against RNN-Based Cyber Anomaly Detection**. *Xu, Jinghui, Yu Wen, Chun Yang, and Dan Meng.* [link](https://ieeexplore.ieee.org/document/9343232) 120 | 121 | * (IJCIP'21) **Adversarial Attacks and Mitigation for Anomaly Detectors of Cyber-Physical Systems**. *Jia, Yifan, Jingyi Wang, Christopher M. Poskitt, Sudipta Chattopadhyay, Jun Sun, and Yuqi Chen.* [link](https://arxiv.org/abs/2105.10707) 122 | 123 | * (S&P'20) **Intriguing properties of adversarial ml attacks in the problem space**. *Pierazzi, Fabio, Feargus Pendlebury, Jacopo Cortellazzi, and Lorenzo Cavallaro*. [link](https://arxiv.org/abs/1911.02142) 124 | 125 | * (ACSAC'20) **Constrained concealment attacks against reconstruction-based anomaly detectors in industrial control systems**. *Erba, Alessandro, Riccardo Taormina, Stefano Galelli, Marcello Pogliani, Michele Carminati, Stefano Zanero, and Nils Ole Tippenhauer* [link](https://arxiv.org/abs/1907.07487) 126 | 127 | * (ICLR'20) **Robust anomaly detection and backdoor attack detection via differential privacy**. *Du, Min, Ruoxi Jia, and Dawn Song.* [link](https://arxiv.org/abs/1911.07116) 128 | 129 | * (AISTATS'10) **Online Anomaly Detection under Adversarial Impact.** *Kloft, Marius, and Pavel Laskov.* [link](http://proceedings.mlr.press/v9/kloft10a.html) 130 | 131 | ## 6. Privacy Preserving Anomaly Detection 132 | 133 | **Perturbation-based Approaches** 134 | * (SIGMOD'21) **PCOR: Private Contextual Outlier Release via Differentially Private Search**. *Masoumeh Shafieinejad, Florian Kerschbaum, and Ihab F. Ilyas.* [link](https://dl.acm.org/doi/10.1145/3448016.3452812) 135 | 136 | * (TII'21) **Security and Privacy-Enhanced Federated Learning for Anomaly Detection in IoT Infrastructures**. *Cui, Lei, Youyang Qu, Gang Xie, Deze Zeng, Ruidong Li, Shigen Shen, and Shui Yu.* [link](https://ieeexplore.ieee.org/document/9522027) 137 | 138 | * (ECML-PKDD'15) **Differentially private analysis of outliers**. *Okada, Rina, Kazuto Fukuchi, and Jun Sakuma.* [link](https://dl.acm.org/doi/10.5555/3120406.3120439) 139 | 140 | * (ICDMW'13) **Differentially Private Anomaly Detection with a Case Study on Epidemic Outbreak Detection**. *Fan, Liyue, and Li Xiong*. [link](https://ieeexplore.ieee.org/document/6754007) 141 | 142 | 143 | **Anonymization-based Approaches** 144 | 145 | * (TSC'19) **An Integrated Framework for Privacy-Preserving Based Anomaly Detection for Cyber-Physical Systems.** *Keshk, Marwa, Elena Sitnikova, Nour Moustafa, Jiankun Hu, and Ibrahim Khalil.* [link](https://ieeexplore.ieee.org/document/8673653) 146 | 147 | **Cryptographic-based approach** 148 | 149 | * (ICDE'20) **Privacy-preserving Real-time Anomaly Detection Using Edge Computing**. *Mehnaz, Shagufta, and Elisa Bertino.* [link](https://ieeexplore.ieee.org/document/9101489) 150 | 151 | * (KIS'15) **Privacy-preserving LOF outlier detection**. *Li, Lu, Liusheng Huang, Wei Yang, Xiaohui Yao, and An Liu*. [link](https://link.springer.com/article/10.1007/s10115-013-0692-0) 152 | 153 | --------------------------------------------------------------------------------