microsoft / DPSDA
Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024]
☆77Updated this week
Related projects ⓘ
Alternatives and complementary repositories for DPSDA
- [ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text☆28Updated last week
- Fast, memory-efficient, scalable optimization of deep learning with differential privacy☆100Updated this week
- Differentially-private transformers using HuggingFace and Opacus☆124Updated 2 months ago
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆70Updated 9 months ago
- Official codes for "Understanding Deep Gradient Leakage via Inversion Influence Functions", NeurIPS 2023☆15Updated last year
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆30Updated 2 years ago
- Algorithms for Privacy-Preserving Machine Learning in JAX☆89Updated 5 months ago
- Official implementation of "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" (ICLR 2022)☆46Updated 2 years ago
- A codebase that makes differentially private training of transformers easy.☆160Updated last year
- Code related to the paper "Machine Unlearning of Features and Labels"☆68Updated 9 months ago
- ☆79Updated 2 years ago
- ☆22Updated 11 months ago
- Differentially Private Diffusion Models☆86Updated 10 months ago
- Code for ML Doctor☆86Updated 3 months ago
- A large labelled image dataset for benchmarking in federated learning☆91Updated 8 months ago
- Membership Inference Competition☆31Updated last year
- ☆22Updated last year
- ☆13Updated last year
- The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word pred…☆86Updated 3 months ago
- ☆57Updated 11 months ago
- ☆16Updated 2 years ago
- ☆32Updated 11 months ago
- Membership Inference Attacks and Defenses in Neural Network Pruning☆28Updated 2 years ago
- [ICLR 2023] Official JAX/Haiku implementation of the paper "Differentially Private Adaptive Optimization with Delayed Preconditioners"☆16Updated last year
- ☆165Updated last year
- ☆38Updated 3 months ago
- ☆13Updated last year
- DP-FTRL from "Practical and Private (Deep) Learning without Sampling or Shuffling" for centralized training.☆25Updated 3 months ago
- This repo implements several algorithms for learning with differential privacy.☆102Updated last year
- code release for "Unrolling SGD: Understanding Factors Influencing Machine Unlearning" published at EuroS&P'22☆22Updated 2 years ago