This repository contains:
- A production-focused API for differentially-private (DP) training of ML models in JAX and Keras.
- A library of core components for implementing differentially private machine learning algorithms in JAX.
- A JAX-based machine learning DP pipeline using components from the library to experiment with image classification models.
This code is open-sourced with the main objective of transparency and reproducibility for research purposes, and includes production-focused APIs for differentially private machine learning. Some rough edges should be expected, especially in the research components.
For installation instructions, examples, and full API documentation, please visit the JAX Privacy documentation.
If you use code from this repository, please cite the following reference:
@software{jax-privacy2022github,
author = {Balle, Borja and Berrada, Leonard and Charles, Zachary and
Choquette-Choo, Christopher A and De, Soham and Doroshenko, Vadym and Dvijotham,
Dj and Galen, Andrew and Ganesh, Arun and Ghalebikesabi, Sahra and Hayes, Jamie
and Kairouz, Peter and McKenna, Ryan and McMahan, Brendan and Pappu, Aneesh and
Ponomareva, Natalia and Pravilov, Mikhail and Rush, Keith and Smith, Samuel L
and Stanforth, Robert and Mishra, Chaitanya},
title = {{JAX}-{P}rivacy: Algorithms for Privacy-Preserving Machine Learning in JAX},
url = {http://github.com/google-deepmind/jax_privacy},
version = {0.4.0},
year = {2025},
}
If you have any questions or feedback, you can contact us via email: jax-privacy-open-source@google.com.
All code is made available under the Apache 2.0 License. Model parameters are made available under the Creative Commons Attribution 4.0 International (CC BY 4.0) License.
See https://creativecommons.org/licenses/by/4.0/legalcode for more details.
This is not an official Google product.