Awesome

DEPRECATION NOTICE

Warning, this repository will soon be deprecated in favor of openmined-website.

Private-Ai-Resources

Private machine learning progress

Content

• About
• Secure and Private AI Course from Udacity
• Secure Deep Learning
• Libraries and Frameworks
• General Research
• Blogs
• Groups
• 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
• Notebooks for Secure and Private AI Course from Udacity
• Advanced PySyft
• Advanced PyGrid

Secure Deep Learning

• PySyft: A Generic Framework for Privacy Preserving Deep Learning
• Private Deep Learning in TensorFlow Using Secure Computation, October 23, 2018
• SecureNN: Efficient and Private Neural Network Training, May 10,2018
• Gazelle: A Low Latency Framework for Secure Neural Network Inference, January 16, 2018
• Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications, November 29, 2017
• CryptoDL: Deep Neural Networks over Encrypted Data, November 14, 2017
• MiniONN: Oblivious Neural Network Predictions via MiniONN Transformations, November 3, 2017
• DeepSecure: Scalable Provably-Secure Deep Learning, May 24, 2017
• SecureML: A System for Scalable Privacy-Preserving Machine Learning, April 19, 2017
• CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy, February 24, 2016
• Privacy-Preserving Deep Learning, October 12, 2015

Libraries and Frameworks

• TinyGarble: Logic Synthesis and Sequential Descriptions for Yao's Garbled Circuits
• SPDZ-2: Multiparty computation with SPDZ and MASCOT offline phase
• ABY: A Framework for Efficient Mixed-Protocol Secure Two-Party Computation
• Obliv - C: C compiler for embedding privacy preserving protocols:
• TFHE: Fast Fully Homomorphic Encryption Library over the Torus
• SEAL: Simple Encypted Arithmatic Library
• PySEAL: Python interface to SEAL
• HElib: An Implementation of homomorphic encryption
• nGraph-HE: Deep learning with Homomorphic Encryption (HE) through Intel nGraph

General Research

• Overdrive: Making SPDZ Great Again
• Privacy-Preserving Logistic Regression Training
• Between a Rock and a Hard Place: Interpolating Between MPC and FHE
• Privacy-Preserving Boosting with Random Linear Classifiers for Learning from User-Generated Data
• The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets
• Improvements for Gate-Hiding Garbled Circuits
• Practical Secure Aggregation for Privacy-Preserving Machine Learning
• CryptoRec: Secure Recommendations as a Service
• Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Differentially Private Generative Adversarial Network
• Doing Real Work with FHE: The Case of Logistic Regression
• ADSNARK: Nearly Practical and Privacy-Preserving Proofs on Authenticated Data
• Scalable Private Learning with PATE
• Doing Real Work with FHE: The Case of Logistic Regression
• Reading in the Dark: Classifying Encrypted Digits with Functional Encryption
• Stealing Hyperparameters in Machine Learning
• How to Backdoor Federated Learning
• Federated Optimization:Distributed Machine Learning for On-Device Intelligence
• Federated Learning: Strategies for Improving Communicating Efficiency
• Personalized and Private Peer-to-Peer Machine Learning
• A generic framework forprivacy preserving deep learning
• Protection Against Reconstruction and Its Applications in Private Federated Learning
• Towards Federated Learning at Scale: System Design
• Federated Learning of Deep Networks using Model Averaging
• SANNS: Scaling Up Secure Approximate k-Nearest Neighbors Search

Blogs

• Cryptography and Machine Learning: Mixing both for private data analysis
• Building Safe A.I.: A Tutorial for Encrypted Deep Learning
• Awesome MPC: Curated List of resources for MPC

Groups

• The Alan Turing Institute: Privacy-preserving data analysis

Podcasts

• TWiML: Differential Privacy Theory & Practice. Aaron Roth
• TWiML: Scalable Differential Privacy for Deep Learning. Nicholas Papernot

Workshops

• Privacy Preserving Machine Learning NeurIPS 2018 Workshop

Thanks

Maintainers

• @gavinuhma
• @iamtrask
• @robert-wagner
• @mortendahl

OpenMined Community

Thanks to members of the OpenMined community who have shared links on slack: @morgangiraud, @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!