google-deepmind / jax_privacyLinks
Algorithms for Privacy-Preserving Machine Learning in JAX
☆94Updated last month
Alternatives and similar repositories for jax_privacy
Users that are interested in jax_privacy are comparing it to the libraries listed below
Sorting:
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆73Updated last year
- ☆80Updated 3 years ago
- Code for Auditing DPSGD☆37Updated 3 years ago
- A codebase that makes differentially private training of transformers easy.☆174Updated 2 years ago
- ☆37Updated 3 years ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆32Updated 3 years ago
- ☆15Updated last year
- Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19☆34Updated 4 years ago
- ☆18Updated 3 years ago
- autodp: A flexible and easy-to-use package for differential privacy☆275Updated last year
- ☆11Updated last year
- Code for fast dpsgd implementations in JAX/TF☆59Updated 2 years ago
- Fast, memory-efficient, scalable optimization of deep learning with differential privacy☆120Updated 2 weeks ago
- Federated posterior averaging implemented in JAX☆51Updated 2 years ago
- ☆22Updated 2 years ago
- A library for running membership inference attacks against ML models☆147Updated 2 years ago
- Code repo for the paper "Privacy-aware Compression for Federated Data Analysis".☆19Updated 2 years ago
- DP-FTRL from "Practical and Private (Deep) Learning without Sampling or Shuffling" for centralized training.☆29Updated this week
- Analytic calibration for differential privacy with Gaussian perturbations☆48Updated 6 years ago
- Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024 Spotlight]☆96Updated this week
- ☆27Updated 2 years ago
- ☆57Updated 4 years ago
- This project's goal is to evaluate the privacy leakage of differentially private machine learning models.☆135Updated 2 years ago
- Public implementation of ICML'19 paper "White-box vs Black-box: Bayes Optimal Strategies for Membership Inference"☆16Updated 5 years ago
- Research and experimental code related to Opacus, an open-source library for training PyTorch models with Differential Privacy☆18Updated 7 months ago
- Differentially-private transformers using HuggingFace and Opacus☆140Updated 9 months ago
- CaPC is a method that enables collaborating parties to improve their own local heterogeneous machine learning models in a setting where b…☆26Updated 3 years ago
- Computationally friendly hyper-parameter search with DP-SGD☆25Updated 4 months ago
- ☆31Updated 9 months ago
- Certified Removal from Machine Learning Models☆65Updated 3 years ago