Installation | Reproducing Results | Citing
This repository contains the JAX implementation of algorithms that we develop in our research on privacy-preserving machine learning. This research code is open-sourced with the main objective of transparency and reproducibility, so (some) rough edges should be expected.
Note: to ensure that your installation is compatible with your local accelerators such as a GPU, we recommend to first follow the corresponding instructions to install TensorFlow and JAX.
This option is preferred for the purpose of re-using functionalities of our
codebase without modifying them.
It does not include the experiments directory, please use
option 2 if you wish to reproduce our results.
The package can be installed by running the following command-line:
pip install git+https://github.com/deepmind/jax_privacy
This option is preferred to either build on top of our codebase or to reproduce our results.
- The first step is to clone the repository:
git clone https://github.com/deepmind/jax_privacy
- Then the code can be installed so that local modifications to the code are reflected in imports of the package:
cd jax_privacy
pip install -e .
Instructions detailed in experiments/image_classification.
This work is available on arXiv at this link. If you use it, please cite the following bibtex reference.
If you use code from this repository, please cite the following reference:
@software{jax-privacy2022github,
author = {Balle, Borja and Berrada, Leonard and De, Soham and Hayes, Jamie and Smith, Samuel L and Stanforth, Robert},
title = {{JAX}-{P}rivacy: Algorithms for Privacy-Preserving Machine Learning in JAX},
url = {http://github.com/deepmind/jax_privacy},
version = {0.1.0},
year = {2022},
}
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.