microsoft / analysing_pii_leakage
The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word prediction language models.
☆84Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for analysing_pii_leakage
- A survey of privacy problems in Large Language Models (LLMs). Contains summary of the corresponding paper along with relevant code☆61Updated 5 months ago
- Differentially-private transformers using HuggingFace and Opacus☆119Updated 2 months ago
- ☆64Updated 2 years ago
- ☆22Updated 11 months ago
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer☆32Updated 5 months ago
- ☆45Updated 4 months ago
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models☆90Updated 3 weeks ago
- A curated list of trustworthy Generative AI papers. Daily updating...☆67Updated 2 months ago
- The code for paper "The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)", exploring the privacy risk o…☆36Updated 8 months ago
- [ICML 2024] Differentially Private Synthetic Data via Foundation Model APIs 2: Text☆28Updated 3 weeks ago
- Official repo for the paper: Recovering Private Text in Federated Learning of Language Models (in NeurIPS 2022)☆57Updated last year
- A toolkit to assess data privacy in LLMs (under development)☆41Updated last month
- A codebase that makes differentially private training of transformers easy.☆158Updated last year
- ☆18Updated 3 years ago
- ☆31Updated last year
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆35Updated 4 months ago
- Python package for measuring memorization in LLMs.☆118Updated last month
- Official Repo of ICLR 24 BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆16Updated 3 months ago
- ☆66Updated 11 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆50Updated 3 months ago
- Training data extraction on GPT-2☆171Updated last year
- LLM security and privacy☆38Updated 3 weeks ago
- ☆35Updated 9 months ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆16Updated 3 months ago
- ☆18Updated 11 months ago
- ☆25Updated 5 months ago
- Code for ML Doctor☆86Updated 2 months ago
- Code and data for our paper "Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark"…☆47Updated last year
- A collection of automated evaluators for assessing jailbreak attempts.☆71Updated 4 months ago
- Repository for Towards Codable Watermarking for Large Language Models☆29Updated last year