microsoft / prv_accountant
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
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆30Updated 2 years ago
- Code for Auditing DPSGD☆37Updated 3 years ago
- Algorithms for Privacy-Preserving Machine Learning in JAX☆93Updated 7 months ago
- A codebase that makes differentially private training of transformers easy.☆168Updated 2 years ago
- Analytic calibration for differential privacy with Gaussian perturbations☆46Updated 6 years ago
- Fast, memory-efficient, scalable optimization of deep learning with differential privacy☆112Updated last month
- ☆80Updated 2 years ago
- autodp: A flexible and easy-to-use package for differential privacy☆270Updated last year
- ☆71Updated 2 years ago
- This project's goal is to evaluate the privacy leakage of differentially private machine learning models.☆130Updated 2 years ago
- Differentially-private transformers using HuggingFace and Opacus☆132Updated 5 months ago
- An implementation of "Data Synthesis via Differentially Private Markov Random Fields"☆11Updated 10 months ago
- This repo implements several algorithms for learning with differential privacy.☆104Updated 2 years ago
- ☆13Updated last year
- A library for running membership inference attacks against ML models☆142Updated 2 years ago
- ☆10Updated 2 years ago
- Code for Canonne-Kamath-Steinke paper https://arxiv.org/abs/2004.00010☆59Updated 4 years ago
- Code for Auditing Data Provenance in Text-Generation Models (in KDD 2019)☆9Updated 5 years ago
- Code for computing tight guarantees for differential privacy☆23Updated last year
- Differentially Private (tabular) Generative Models Papers with Code☆45Updated 7 months ago
- Concentrated Differentially Private Gradient Descent with Adaptive per-iteration Privacy Budget☆49Updated 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
- Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19☆34Updated 3 years ago
- Hadamard Response: Communication efficient, sample optimal, linear time locally private learning of distributions☆14Updated 4 years ago
- ☆27Updated 2 years ago
- Systematic Evaluation of Membership Inference Privacy Risks of Machine Learning Models☆125Updated 10 months ago
- Implementation of calibration bounds for differential privacy in the shuffle model☆23Updated 4 years ago
- [CCS 2021] "DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation" by Boxin Wang*, Fan Wu*, Yunhui Long…☆37Updated 3 years ago
- This repository contains the codes for first large-scale investigation of Differentially Private Convex Optimization algorithms.☆63Updated 6 years ago
- ☆45Updated 5 years ago