apple / ml-shuffling-amplification
☆17Updated 2 years ago
Related projects: ⓘ
- Fast, memory-efficient, scalable optimization of deep learning with differential privacy☆86Updated last week
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆64Updated 7 months ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆29Updated 2 years ago
- ☆38Updated 2 years ago
- Research and experimental code related to Opacus, an open-source library for training PyTorch models with Differential Privacy☆17Updated 2 months ago
- [ICLR 2024] Generating DP Synthetic Data without Training☆74Updated 5 months ago
- Multiple Frequency Estimation Under Local Differential Privacy in Python☆41Updated last year
- Membership Inference Competition☆30Updated last year
- ☆77Updated 2 years ago
- Analytic calibration for differential privacy with Gaussian perturbations☆44Updated 5 years ago
- Web application that makes data releases that satisfy differential privacy using the OpenDP Library☆19Updated last month
- This repo contains the underlying code for all the experiments from the paper: "Automatic Discovery of Privacy-Utility Pareto Fronts"☆26Updated last year
- ☆23Updated 8 months ago
- Code for Canonne-Kamath-Steinke paper https://arxiv.org/abs/2004.00010☆59Updated 4 years ago
- ☆42Updated 3 years ago
- ☆21Updated last year
- Data61' CSIRO Distributed System Security Group. We have developed this algorithm to explore the question - Can We Use Split Learning on …☆12Updated 7 months ago
- DP-FTRL from "Practical and Private (Deep) Learning without Sampling or Shuffling" for centralized training.☆24Updated last month
- Algorithms for Privacy-Preserving Machine Learning in JAX☆87Updated 3 months ago
- [NeurIPS 2021] "G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators" by Yunhui Long*…☆30Updated 2 years ago
- [ICML 2024] Differentially Private Synthetic Data via Foundation Model APIs 2: Text☆24Updated 3 months ago
- PrivGAN: Protecting GANs from membership inference attacks at low cost☆28Updated 3 months ago
- Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19☆34Updated 3 years ago
- 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
- A SMPC companion library for Syft☆98Updated last month
- This project's goal is to evaluate the privacy leakage of differentially private machine learning models.☆129Updated last year
- Code for fast dpsgd implementations in JAX/TF☆58Updated last year
- Code for computing tight guarantees for differential privacy☆21Updated last year
- This repository contains the codes for first large-scale investigation of Differentially Private Convex Optimization algorithms.☆63Updated 5 years ago
- Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness (IJCAI'19).☆13Updated 3 years ago