Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mortendahl/awesome-ppml
A curated list of resources for privacy-preserving machine learning
https://github.com/mortendahl/awesome-ppml
List: awesome-ppml
Last synced: 11 days ago
JSON representation
A curated list of resources for privacy-preserving machine learning
- Host: GitHub
- URL: https://github.com/mortendahl/awesome-ppml
- Owner: mortendahl
- Created: 2018-12-10T18:41:20.000Z (about 6 years ago)
- Default Branch: master
- Last Pushed: 2021-10-19T12:25:02.000Z (about 3 years ago)
- Last Synced: 2024-05-23T02:07:27.843Z (7 months ago)
- Size: 13.7 KB
- Stars: 147
- Watchers: 10
- Forks: 28
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-ppdm - awesome-ppml
- ultimate-awesome - awesome-ppml - A curated list of resources for privacy-preserving machine learning. (Other Lists / Monkey C Lists)
README
# Awesome PPML
A curated list of resources for privacy-preserving machine learning.
See also:
- [awesome-he](https://github.com/jonaschn/awesome-he) - for homomorphic encryption
- [awesome-mpc](https://github.com/rdragos/awesome-mpc) - for secure multi-party computation
- [awesome-differential-privacy](https://github.com/menisadi/awesome-differential-privacy) - for differential privacy
which also contain links to some of the (more general purpose) tools often used in with PPML.
## News and Updates
- [PPML News](https://ppml-news.github.io) and [updates on Twitter](https://twitter.com/ppml_news)
- [IACR ePrint archive](https://eprint.iacr.org/eprint-bin/search.pl?last=31) and [updates on Twitter](https://twitter.com/IACRePrint)
- [Cryptography and Security on arXiv.org](https://arxiv.org/list/cs.CR/recent)
- [Machine Learning on arXiv.org](https://arxiv.org/list/stat.ML/recent)
## Software
- [HE Transformer](https://github.com/NervanaSystems/he-transformer) - homomorphic encryption backend for nGraph
- [TensorFlow Privacy](https://github.com/tensorflow/privacy) - differential privacy in TensorFlow
- [TensorFlow Federated](https://github.com/tensorflow/federated) - federated learning in TensorFlow
- [TF Encrypted](https://github.com/tf-encrypted/) - encrypted machine learning in TensorFlow
- [PySyft](https://github.com/OpenMined/PySyft) - encrypted, privacy preserving machine learning in PyTorch and TensorFlow
## Conferences and Workshops
- [Privacy-Preserving Machine Learning](https://ppml-workshop.github.io/ppml/)
- [Hacking Deep Learning](https://cyber.biu.ac.il/event/hacking-deep-learning/)
- [Private Multi-Party Machine Learning, NIPS'16](https://pmpml.github.io/PMPML16/)
## Tutorials and Courses
- [Privacy-Preserving Machine Learning with TensorFlow, TFWorld'19](https://github.com/dropoutlabs/tf-world-tutorial)
- [Secure and Private AI, Udacity](https://www.udacity.com/course/secure-and-private-ai--ud185)
- [Privacy Preserving Deep Learning with PyTorch & PySyft](https://github.com/OpenMined/PySyft/tree/master/examples/tutorials)
## Research Papers
A great summary is provided in [MRSV'17](https://eprint.iacr.org/2017/1190) and the archives of [PPML News](https://ppml-news.github.io) contain more papers in chronological order.
Selection:
- [*Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference*, CBLYHF'18](https://arxiv.org/abs/1811.09953)
- [*nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data*, BLW'18](https://arxiv.org/abs/1810.10121)
- [*CHET: Compiler and Runtime for Homomorphic Evaluation of Tensor Programs*, DSCLLMMM'18](https://arxiv.org/abs/1810.00845)
- [*Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware*, TB'18](https://arxiv.org/abs/1806.03287)
- [*SecureNN: Efficient and Private Neural Network Traning*, WGC'18](https://eprint.iacr.org/2018/442)
- [*ABY3: A Mixed Protocol Framework for Machine Learning*, MR'18](https://eprint.iacr.org/2018/403)
- [*Chiron: Privacy-preserving Machine Learning as a Service*, HSSSW'18](https://arxiv.org/abs/1803.05961)
- [*Scalable Private Learning with PATE*, PSMRTE'18](https://arxiv.org/abs/1802.08908)
- [*EPIC: Efficient Private Image Classification*, MRSV'17](https://eprint.iacr.org/2017/1190)
- [*Gazelle: A Low Latency Framework for Secure Neural Network Inference*, JVC'18](https://eprint.iacr.org/2018/073)
- [*Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications*, RWTSSK'17](https://eprint.iacr.org/2017/1164)
- [*DeepSecure: Scalable Provably-Secure Deep Learning*, RRK'17](https://arxiv.org/abs/1705.08963)
- [*Oblivious Neural Network Predictions via MiniONN transformations*, LJLA'17](https://eprint.iacr.org/2017/452)
- [*SecureML: A System for Scalable Privacy-Preserving Machine Learning*, MZ'17](https://eprint.iacr.org/2017/396)
- [*CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy*, DGLLNW'16](https://www.microsoft.com/en-us/research/publication/cryptonets-applying-neural-networks-to-encrypted-data-with-high-throughput-and-accuracy/)