microsoft / analysing_pii_leakageLinks
The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word prediction language models.
☆97Updated 11 months ago
Alternatives and similar repositories for analysing_pii_leakage
Users that are interested in analysing_pii_leakage are comparing it to the libraries listed below
Sorting:
- A survey of privacy problems in Large Language Models (LLMs). Contains summary of the corresponding paper along with relevant code☆67Updated last year
- Differentially-private transformers using HuggingFace and Opacus☆139Updated 10 months ago
- ☆74Updated 3 years ago
- ☆56Updated 4 months ago
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer☆44Updated last year
- The code for paper "The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)", exploring the privacy risk o…☆50Updated 5 months ago
- A curated list of trustworthy Generative AI papers. Daily updating...☆73Updated 10 months ago
- A toolkit to assess data privacy in LLMs (under development)☆59Updated 6 months ago
- ☆26Updated last year
- Python package for measuring memorization in LLMs.☆159Updated this week
- Unofficial implementation of "Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection"☆20Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆81Updated 9 months ago
- Training data extraction on GPT-2☆188Updated 2 years ago
- ☆104Updated last year
- A Comprehensive Assessment of Trustworthiness in GPT Models☆294Updated 9 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆135Updated 11 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆130Updated 3 months ago
- ☆44Updated 5 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆58Updated last week
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆307Updated last year
- ☆175Updated last year
- A codebase that makes differentially private training of transformers easy.☆175Updated 2 years ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆157Updated last year
- LLM Self Defense: By Self Examination, LLMs know they are being tricked☆39Updated last year
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models☆170Updated 4 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆43Updated last month
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆128Updated last month
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆161Updated 3 months ago
- A Synthetic Dataset for Personal Attribute Inference (NeurIPS'24 D&B)☆43Updated 7 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆157Updated 6 months ago