microsoft / prv_accountantLinks
A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.
☆76Updated 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:
- autodp: A flexible and easy-to-use package for differential privacy☆278Updated 2 years ago
- Code for Auditing DPSGD☆37Updated 3 years ago
- ☆80Updated 3 years ago
- A codebase that makes differentially private training of transformers easy.☆182Updated 3 years ago
- Fast, memory-efficient, scalable optimization of deep learning with differential privacy☆135Updated 3 weeks ago
- Analytic calibration for differential privacy with Gaussian perturbations☆51Updated 7 years ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆32Updated 3 years ago
- This project's goal is to evaluate the privacy leakage of differentially private machine learning models.☆135Updated 3 years ago
- A library for running membership inference attacks against ML models☆152Updated 3 years ago
- DP-FTRL from "Practical and Private (Deep) Learning without Sampling or Shuffling" for centralized training.☆35Updated 7 months ago
- This repo implements several algorithms for learning with differential privacy.☆111Updated 3 years ago
- Algorithms for Privacy-Preserving Machine Learning in JAX☆136Updated 2 weeks ago
- ☆77Updated 3 years ago
- Code for Canonne-Kamath-Steinke paper https://arxiv.org/abs/2004.00010☆63Updated 5 years ago
- Differentially-private transformers using HuggingFace and Opacus☆145Updated last year
- Hadamard Response: Communication efficient, sample optimal, linear time locally private learning of distributions☆16Updated 5 years ago
- Code repo for the paper "Privacy-aware Compression for Federated Data Analysis".☆19Updated 2 years ago
- Systematic Evaluation of Membership Inference Privacy Risks of Machine Learning Models☆132Updated last year
- simple Differential Privacy in PyTorch☆49Updated 5 years ago
- ☆15Updated 2 years ago
- Research and experimental code related to Opacus, an open-source library for training PyTorch models with Differential Privacy☆18Updated last year
- Code for Exploiting Unintended Feature Leakage in Collaborative Learning (in Oakland 2019)☆56Updated 6 years ago
- Code for Membership Inference Attack against Machine Learning Models (in Oakland 2017)☆200Updated 8 years ago
- This repository contains the codes for first large-scale investigation of Differentially Private Convex Optimization algorithms.☆63Updated 7 years ago
- Code for Auditing Data Provenance in Text-Generation Models (in KDD 2019)☆10Updated 6 years ago
- Breaching privacy in federated learning scenarios for vision and text☆310Updated last week
- A library providing general-purpose tools for estimating discrete distributions from noisy observations of their marginals.☆110Updated this week
- Code for computing tight guarantees for differential privacy☆23Updated 2 years ago
- ☆46Updated 6 years ago
- ☆27Updated 3 years ago