microsoft / DPSDA
[ICLR 2024] Generating DP Synthetic Data without Training
☆74Updated 5 months ago
Related projects: ⓘ
- Fast, memory-efficient, scalable optimization of deep learning with differential privacy☆86Updated last week
- [ICML 2024] Differentially Private Synthetic Data via Foundation Model APIs 2: Text☆24Updated 2 months ago
- Differentially-private transformers using HuggingFace and Opacus☆108Updated 3 weeks ago
- Differentially Private Diffusion Models☆77Updated 8 months ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆29Updated 2 years ago
- ☆56Updated 8 months ago
- Algorithms for Privacy-Preserving Machine Learning in JAX☆87Updated 3 months ago
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer☆28Updated 3 months ago
- ☆21Updated 9 months ago
- ☆77Updated 2 years ago
- A large labelled image dataset for benchmarking in federated learning☆88Updated 6 months ago
- code release for "Unrolling SGD: Understanding Factors Influencing Machine Unlearning" published at EuroS&P'22☆22Updated 2 years ago
- ☆21Updated last year
- [NeurIPS 2021] "G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators" by Yunhui Long*…☆30Updated 2 years ago
- A codebase that makes differentially private training of transformers easy.☆151Updated last year
- Private Adaptive Optimization with Side Information (ICML '22)☆16Updated 2 years ago
- Membership Inference Competition☆30Updated last year
- ☆31Updated 9 months ago
- DP-FTRL from "Practical and Private (Deep) Learning without Sampling or Shuffling" for centralized training.☆24Updated last month
- ☆16Updated 2 years ago
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆64Updated 7 months ago
- ☆13Updated last year
- Official implementation of "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" (ICLR 2022)☆45Updated 2 years ago
- [ICML 2022 / ICLR 2024] Source code for our papers "Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks" and "Be C…☆34Updated last month
- ☆23Updated 8 months ago
- ☆10Updated 2 years ago
- Official codes for "Understanding Deep Gradient Leakage via Inversion Influence Functions", NeurIPS 2023☆14Updated 11 months ago
- Code for ML Doctor☆84Updated last month
- Code related to the paper "Machine Unlearning of Features and Labels"☆66Updated 7 months ago
- Implementation of the paper: "FedTabDiff: Federated Learning of Diffusion Models for Synthetic Mixed-Type Tabular Data Generation"☆12Updated last month