apple / ml-shuffling-amplification
☆18Updated 2 years ago
Alternatives and similar repositories for ml-shuffling-amplification:
Users that are interested in ml-shuffling-amplification are comparing it to the libraries listed below
- ☆10Updated last year
- Research and experimental code related to Opacus, an open-source library for training PyTorch models with Differential Privacy☆17Updated 3 months ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆30Updated 2 years ago
- Code for Canonne-Kamath-Steinke paper https://arxiv.org/abs/2004.00010☆59Updated 4 years ago
- ☆38Updated 2 years ago
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆73Updated 11 months ago
- Fast, memory-efficient, scalable optimization of deep learning with differential privacy☆110Updated last week
- Multiple Frequency Estimation Under Local Differential Privacy in Python☆42Updated last year
- Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024]☆84Updated this week
- Unified, Simplified, Tight and Fast Privacy Amplification in the Shuffle Model of Differential Privacy☆10Updated 2 months ago
- Hadamard Response: Communication efficient, sample optimal, linear time locally private learning of distributions☆14Updated 4 years ago
- Web application that makes data releases that satisfy differential privacy using the OpenDP Library☆20Updated 5 months ago
- Code to accompany the paper "Deep Learning with Gaussian Differential Privacy"☆31Updated 3 years ago
- ☆80Updated 2 years ago
- Membership Inference Competition☆31Updated last year
- ☆23Updated last year
- ☆22Updated 2 years ago
- ☆43Updated 3 years ago
- Analytic calibration for differential privacy with Gaussian perturbations☆46Updated 6 years ago
- PyTorch implementation of a number of mechanisms in local differential privacy☆15Updated 2 years ago
- Differentially Private Conditional Generative Adversarial Network☆30Updated 3 years ago
- DP-FTRL from "Practical and Private (Deep) Learning without Sampling or Shuffling" for centralized training.☆26Updated 5 months ago
- DP-HyperparamTuning offers an array of tools for fast and easy hypertuning of various hyperparameters for the DP-SGD algorithm.☆24Updated 3 years ago
- Github pages backend for https://differentialprivacy.org☆25Updated 7 months ago
- Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19☆35Updated 3 years ago
- This repo contains the underlying code for all the experiments from the paper: "Automatic Discovery of Privacy-Utility Pareto Fronts"☆27Updated 2 years ago
- Code for the CCS'22 paper "Federated Boosted Decision Trees with Differential Privacy"☆43Updated last year
- CaPC is a method that enables collaborating parties to improve their own local heterogeneous machine learning models in a setting where b…☆26Updated 2 years ago
- This project's goal is to evaluate the privacy leakage of differentially private machine learning models.☆130Updated 2 years ago
- Code for Auditing DPSGD☆38Updated 2 years ago