└── README.md


/README.md:
--------------------------------------------------------------------------------
 1 | # awesome privacy-preserving machine learning
 2 | This repository is used to summarize the latest research progress of privacy-preserving machine learning (PPML)，privacy-preserving deep learning (PPDL)
 3 | 
 4 | 
 5 | 
 6 | ## Table of Contents
 7 | 
 8 |  - [Federated Learning](#federated-learning)
 9 |  - [Differential Privacy](#differential-privacy)
10 |  - [PATE](#pate)
11 |  - [Homomorphic Encryption](#homomorphic-encryption)
12 |  - [Secure Multi-Party Computation](#secure-multi-party-computation)
13 | 
14 | 
15 | 
16 | ## Federated Learning
17 | 
18 | Some related github repositories 
19 | 
20 | * [poga/awesome-federated-learning](https://github.com/poga/awesome-federated-learning)
21 | 
22 | * [timmers/awesome-federated-learning](https://github.com/timmers/awesome-federated-learning)
23 | * [innovation-cat/Awesome-Federated-Machine-Learning](https://github.com/innovation-cat/Awesome-Federated-Machine-Learning)
24 | 
25 | 
26 | 
27 | ## Differential Privacy
28 | 
29 | ### Blog 
30 | 
31 | * [Why differential privacy is awesome](https://desfontain.es/privacy/differential-privacy-awesomeness.html)
32 | 
33 | 
34 | ### Papers
35 | 
36 | * [Deep Learning with Differential Privacy](https://arxiv.org/abs/1607.00133) - arXiv 2016
37 | 
38 | * [Differentially Private Federated Learning: A Client Level Perspective](https://arxiv.org/abs/1712.07557v2) - arXiv 2016
39 | 
40 | * [Learning differentially private recurrent language models](https://openreview.net/pdf?id=BJ0hF1Z0b) - ICLR 2018
41 | 
42 |   
43 | 
44 | ## PATE
45 | 
46 | The PATE ('Private Aggregation of Teacher Ensembles') framework was introduced by Papernot et al. Strictly speaking, PATE is one of implementations of differential privacy, this framework enables model-agnostic training that provably provides differential privacy of the training dataset.
47 | 
48 | * [Scalable Private Learning with PATE](https://arxiv.org/abs/1802.08908) - ICLR 2018 
49 | 
50 | * [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://arxiv.org/abs/1610.05755) - ICLR 2017
51 | 
52 |   
53 | 
54 | ## Homomorphic Encryption
55 | 
56 | * [SHE: A Fast and Accurate Deep Neural Network for Encrypted Data](https://papers.nips.cc/paper/9194-she-a-fast-and-accurate-deep-neural-network-for-encrypted-data.pdf) - NeurIPS 2019
57 | * [Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference](https://arxiv.org/abs/1811.09953) - arXiv 2018
58 | * [The AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data with GPUs](https://arxiv.org/abs/1811.00778) - arXiv 2018
59 | * [CryptoDL: Deep Neural Networks over Encrypted Data](https://arxiv.org/abs/1711.05189) - arXiv 2017
60 | * [Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption](https://arxiv.org/abs/1711.10677) - arXiv 2017 (Apply additively homomorphic encryption algorithm to Federated Learning)
61 | * [CryptoNets: applying neural networks to encrypted data with high throughput and accuracy](http://proceedings.mlr.press/v48/gilad-bachrach16.pdf) - ICML 2016
62 | 
63 | 
64 | 
65 | ## Secure Multi-Party Computation
66 | 
67 | 
68 | 
69 | 


--------------------------------------------------------------------------------