microsoft / prv_accountantLinks
A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.
☆73Updated last year
Alternatives and similar repositories for prv_accountant
Users that are interested in prv_accountant are comparing it to the libraries listed below
Sorting:
- Code for Auditing DPSGD☆37Updated 3 years ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆32Updated 3 years ago
- ☆80Updated 3 years ago
- A codebase that makes differentially private training of transformers easy.☆175Updated 2 years ago
- Algorithms for Privacy-Preserving Machine Learning in JAX☆96Updated last week
- autodp: A flexible and easy-to-use package for differential privacy☆274Updated last year
- Fast, memory-efficient, scalable optimization of deep learning with differential privacy☆128Updated last month
- Analytic calibration for differential privacy with Gaussian perturbations☆49Updated 6 years ago
- This project's goal is to evaluate the privacy leakage of differentially private machine learning models.☆136Updated 2 years ago
- A library for running membership inference attacks against ML models☆149Updated 2 years ago
- DP-FTRL from "Practical and Private (Deep) Learning without Sampling or Shuffling" for centralized training.☆30Updated 3 months ago
- Differentially-private transformers using HuggingFace and Opacus☆141Updated last year
- This repo implements several algorithms for learning with differential privacy.☆109Updated 2 years ago
- ☆75Updated 3 years ago
- Code for Canonne-Kamath-Steinke paper https://arxiv.org/abs/2004.00010☆59Updated 5 years ago
- This repository contains the codes for first large-scale investigation of Differentially Private Convex Optimization algorithms.☆63Updated 6 years ago
- [NeurIPS 2021] "G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators" by Yunhui Long*…☆30Updated 3 years ago
- Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024 Spotlight]☆101Updated last week
- ☆15Updated 2 years ago
- Code for Exploiting Unintended Feature Leakage in Collaborative Learning (in Oakland 2019)☆54Updated 6 years ago
- Systematic Evaluation of Membership Inference Privacy Risks of Machine Learning Models☆128Updated last year
- Research and experimental code related to Opacus, an open-source library for training PyTorch models with Differential Privacy☆18Updated 11 months ago
- Code for Membership Inference Attack against Machine Learning Models (in Oakland 2017)☆194Updated 7 years ago
- Hadamard Response: Communication efficient, sample optimal, linear time locally private learning of distributions☆15Updated 4 years ago
- Breaching privacy in federated learning scenarios for vision and text☆304Updated 3 weeks ago
- Implementation of the paper : "Membership Inference Attacks Against Machine Learning Models", Shokri et al.☆58Updated 6 years ago
- ☆20Updated 2 years ago
- [ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text☆43Updated 8 months ago
- A library providing general-purpose tools for estimating discrete distributions from noisy observations of their marginals.☆105Updated 2 weeks ago
- ☆27Updated 2 years ago