lxuechen / private-transformersLinks
A codebase that makes differentially private training of transformers easy.
☆176Updated 2 years ago
Alternatives and similar repositories for private-transformers
Users that are interested in private-transformers are comparing it to the libraries listed below
Sorting:
- Differentially-private transformers using HuggingFace and Opacus☆143Updated last year
- ☆75Updated 3 years ago
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆74Updated last year
- Code for Auditing DPSGD☆37Updated 3 years ago
- Algorithms for Privacy-Preserving Machine Learning in JAX☆105Updated last month
- Training data extraction on GPT-2☆192Updated 2 years ago
- Fast, memory-efficient, scalable optimization of deep learning with differential privacy☆130Updated last month
- ☆80Updated 3 years ago
- ☆21Updated 4 years ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆32Updated 3 years ago
- This repo implements several algorithms for learning with differential privacy.☆109Updated 2 years ago
- Code for Auditing Data Provenance in Text-Generation Models (in KDD 2019)☆10Updated 6 years ago
- Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024 Spotlight]☆102Updated 2 weeks ago
- Official repo for the paper: Recovering Private Text in Federated Learning of Language Models (in NeurIPS 2022)☆59Updated 2 years ago
- The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word pred…☆101Updated last year
- [ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text☆46Updated 8 months ago
- Systematic Evaluation of Membership Inference Privacy Risks of Machine Learning Models☆127Updated last year
- autodp: A flexible and easy-to-use package for differential privacy☆275Updated last year
- A survey of privacy problems in Large Language Models (LLMs). Contains summary of the corresponding paper along with relevant code☆67Updated last year
- ☆294Updated 2 months ago
- ☆194Updated 2 years ago
- DP-FTRL from "Practical and Private (Deep) Learning without Sampling or Shuffling" for centralized training.☆30Updated 4 months ago
- Certified Removal from Machine Learning Models☆69Updated 4 years ago
- ☆22Updated 4 years ago
- ☆30Updated 4 years ago
- A library for running membership inference attacks against ML models☆150Updated 2 years ago
- ☆355Updated 3 months ago
- Membership Inference Competition☆31Updated 2 years ago
- ☆30Updated last year
- Breaching privacy in federated learning scenarios for vision and text☆306Updated last month