https://github.com/openmined/private-ai-resources
SOON TO BE DEPRECATED - Private machine learning progress
https://github.com/openmined/private-ai-resources
writing
Last synced: 6 months ago
JSON representation
SOON TO BE DEPRECATED - Private machine learning progress
- Host: GitHub
- URL: https://github.com/openmined/private-ai-resources
- Owner: OpenMined
- License: mit
- Created: 2018-03-07T02:06:10.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2020-05-16T18:05:36.000Z (over 5 years ago)
- Last Synced: 2025-06-07T00:40:33.028Z (7 months ago)
- Topics: writing
- Homepage:
- Size: 40 KB
- Stars: 470
- Watchers: 44
- Forks: 99
- Open Issues: 8
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# DEPRECATION NOTICE
Warning, this repository will soon be deprecated in favor of [openmined-website](https://github.com/OpenMined/openmined-website).
# Private-Ai-Resources
Private machine learning progress
## Content
- [About](#about)
- [Secure and Private AI Course from Udacity](#secure-and-private-ai-course)
- [Secure Deep Learning](#secure-deep-learning)
- [Libraries and Frameworks](#libraries-and-frameworks)
- [General Research](#general-research)
- [Blogs](#blogs)
- [Groups](#groups)
- [Thanks](#thanks)
# About
This is a curated list of resources related to the research and development of private machine learning.
# Secure and Private AI Course
* [Secure and Private AI Course from Udacity](https://www.udacity.com/course/secure-and-private-ai--ud185)
* [Notebooks for Secure and Private AI Course from Udacity](https://github.com/udacity/private-ai)
* [Advanced PySyft](https://github.com/OpenMined/PySyft/tree/master/examples/tutorials)
* [Advanced PyGrid](https://github.com/OpenMined/PyGrid/tree/dev/examples)
# Secure Deep Learning
* [PySyft: A Generic Framework for Privacy Preserving Deep Learning](https://arxiv.org/abs/1811.04017)
* [Private Deep Learning in TensorFlow Using Secure Computation, October 23, 2018](https://arxiv.org/abs/1810.08130)
* [SecureNN: Efficient and Private Neural Network Training, May 10,2018](https://eprint.iacr.org/2018/442.pdf)
* [Gazelle: A Low Latency Framework for Secure Neural Network Inference, January 16, 2018](https://arxiv.org/abs/1801.05507)
* [Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications, November 29, 2017](https://eprint.iacr.org/2017/1164)
* [CryptoDL: Deep Neural Networks over Encrypted Data, November 14, 2017](https://arxiv.org/abs/1711.05189)
* [MiniONN: Oblivious Neural Network Predictions via MiniONN
Transformations, November 3, 2017](https://acmccs.github.io/papers/p619-liuA.pdf)
* [DeepSecure: Scalable Provably-Secure Deep Learning, May 24, 2017](https://arxiv.org/abs/1705.08963)
* [SecureML: A System for Scalable Privacy-Preserving Machine Learning, April 19, 2017](https://eprint.iacr.org/2017/396)
* [CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy, February 24, 2016](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/04/CryptonetsTechReport.pdf)
* [Privacy-Preserving Deep Learning, October 12, 2015](https://dl.acm.org/citation.cfm?id=2813687)
# Libraries and Frameworks
* [TinyGarble: Logic Synthesis and Sequential Descriptions for Yao's Garbled Circuits](https://github.com/esonghori/TinyGarble)
* [SPDZ-2: Multiparty computation with SPDZ and MASCOT offline phase](https://github.com/bristolcrypto/SPDZ-2)
* [ABY: A Framework for Efficient Mixed-Protocol Secure Two-Party Computation](https://github.com/encryptogroup/aby)
* [Obliv - C: C compiler for embedding privacy preserving protocols:](http://oblivc.org/)
* [TFHE: Fast Fully Homomorphic Encryption Library over the Torus](https://github.com/tfhe/tfhe)
* [SEAL: Simple Encypted Arithmatic Library](https://www.microsoft.com/en-us/research/project/simple-encrypted-arithmetic-library/)
* [PySEAL: Python interface to SEAL](https://github.com/Lab41/PySEAL)
* [HElib: An Implementation of homomorphic encryption](https://github.com/shaih/HElib)
* [nGraph-HE: Deep learning with Homomorphic Encryption (HE) through Intel nGraph](https://github.com/NervanaSystems/he-transformer)
# General Research
* [Overdrive: Making SPDZ Great Again](https://eprint.iacr.org/2017/1230)
* [Privacy-Preserving Logistic Regression Training](https://eprint.iacr.org/2018/233)
* [Between a Rock and a Hard Place: Interpolating Between MPC and FHE](https://eprint.iacr.org/2013/085.pdf)
* [Privacy-Preserving Boosting with Random Linear Classifiers for Learning from User-Generated Data](https://arxiv.org/abs/1802.08288)
* [The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets](https://arxiv.org/abs/1802.08232)
* [Improvements for Gate-Hiding Garbled Circuits](https://eprint.iacr.org/2017/976.pdf)
* [Practical Secure Aggregation for Privacy-Preserving Machine Learning](https://eprint.iacr.org/2017/281.pdf)
* [CryptoRec: Secure Recommendations as a Service](https://arxiv.org/pdf/1802.02432.pdf)
* [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://arxiv.org/abs/1610.05755)
* [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://arxiv.org/abs/1602.05629)
* [Differentially Private Generative Adversarial Network](https://arxiv.org/abs/1802.06739)
* [Doing Real Work with FHE: The Case of Logistic Regression](https://eprint.iacr.org/2018/202)
* [ADSNARK: Nearly Practical and Privacy-Preserving Proofs on Authenticated Data](https://eprint.iacr.org/2014/617.pdf)
* [Scalable Private Learning with PATE](https://arxiv.org/abs/1802.08908)
* [Doing Real Work with FHE: The Case of Logistic Regression](https://eprint.iacr.org/2018/202)
* [Reading in the Dark: Classifying Encrypted Digits with Functional Encryption](https://eprint.iacr.org/2018/206)
* [Stealing Hyperparameters in Machine Learning](https://arxiv.org/abs/1802.05351)
* [How to Backdoor Federated Learning](https://arxiv.org/abs/1807.00459)
* [Federated Optimization:Distributed Machine Learning for On-Device Intelligence](https://arxiv.org/abs/1610.02527)
* [Federated Learning: Strategies for Improving Communicating Efficiency](https://arxiv.org/abs/1610.05492)
* [Personalized and Private Peer-to-Peer Machine Learning](http://proceedings.mlr.press/v84/bellet18a/bellet18a.pdf)
* [A generic framework forprivacy preserving deep learning](https://arxiv.org/abs/1811.04017)
* [Protection Against Reconstruction and Its Applications in Private Federated Learning](https://arxiv.org/abs/1812.00984)
* [Towards Federated Learning at Scale: System Design](https://arxiv.org/abs/1902.01046)
* [Federated Learning of Deep Networks using Model Averaging](https://arxiv.org/abs/1602.05629)
* [SANNS: Scaling Up Secure Approximate k-Nearest Neighbors Search](https://arxiv.org/abs/1904.02033)
# Blogs
* [Cryptography and Machine Learning: Mixing both for private data analysis](https://mortendahl.github.io/)
* [Building Safe A.I.: A Tutorial for Encrypted Deep Learning](https://iamtrask.github.io/2017/03/17/safe-ai/)
* [Awesome MPC: Curated List of resources for MPC](https://github.com/rdragos/awesome-mpc)
# Groups
* [The Alan Turing Institute: Privacy-preserving data analysis](https://www.turing.ac.uk/research_projects/privacy-preserving-data-analysis/)
# Podcasts
* [TWiML: Differential Privacy Theory & Practice. Aaron Roth](https://twimlai.com/talk/132)
* [TWiML: Scalable Differential Privacy for Deep Learning. Nicholas Papernot](https://twimlai.com/talk/134)
# Workshops
* [Privacy Preserving Machine Learning NeurIPS 2018 Workshop](https://ppml-workshop.github.io/ppml/)
# Thanks
### Maintainers
* [@gavinuhma](https://github.com/gavinuhma)
* [@iamtrask](https://github.com/iamtrask)
* [@robert-wagner](https://github.com/robert-wagner)
* [@mortendahl](https://github.com/mortendahl)
### OpenMined Community
Thanks to members of the OpenMined community who have shared links on slack: [@morgangiraud](https://github.com/morgangiraud), [@jvmancuso](https://github.com/jvmancuso)
### Adding links
If you have any links to add please send a pull request, and we'll take a look. There is so much happening in this space!