AI-secure / aug-peLinks
[ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text
☆46Updated 9 months ago
Alternatives and similar repositories for aug-pe
Users that are interested in aug-pe are comparing it to the libraries listed below
Sorting:
- Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024 Spotlight]☆103Updated last month
- Differentially-private transformers using HuggingFace and Opacus☆143Updated last year
- A codebase that makes differentially private training of transformers easy.☆176Updated 2 years ago
- ☆28Updated last year
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer☆46Updated last year
- ☆10Updated 3 years ago
- A toolkit to assess data privacy in LLMs (under development)☆62Updated 9 months ago
- Python package for measuring memorization in LLMs.☆170Updated 3 months 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
- ☆75Updated 3 years ago
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆74Updated last year
- ☆21Updated 4 years ago
- ☆23Updated 2 years ago
- A survey of privacy problems in Large Language Models (LLMs). Contains summary of the corresponding paper along with relevant code☆68Updated last year
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆89Updated last year
- Official repo for the paper: Recovering Private Text in Federated Learning of Language Models (in NeurIPS 2022)☆61Updated 2 years ago
- The collection of papers about Private Evolution☆17Updated 2 weeks ago
- Code for watermarking language models☆82Updated last year
- Fast, memory-efficient, scalable optimization of deep learning with differential privacy☆132Updated 2 months ago
- ☆12Updated 4 months ago
- A Synthetic Dataset for Personal Attribute Inference (NeurIPS'24 D&B)☆45Updated 2 months ago
- ☆46Updated 8 months ago
- [EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156☆40Updated last year
- ☆31Updated last year
- ☆69Updated 8 months ago
- Private Adaptive Optimization with Side Information (ICML '22)☆16Updated 3 years ago
- Official github page for the paper "Evaluating Deep Unlearning in Large Language Model"☆14Updated 6 months ago
- ☆45Updated last year
- ☆111Updated last year
- ☆58Updated 2 years ago