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.
☆101Updated last year
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☆68Updated last year
- Differentially-private transformers using HuggingFace and Opacus☆145Updated last year
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer☆46Updated last year
- ☆70Updated 9 months ago
- ☆76Updated 3 years ago
- ☆29Updated 2 years ago
- Python package for measuring memorization in LLMs.☆175Updated 4 months ago
- A curated list of trustworthy Generative AI papers. Daily updating...☆75Updated last year
- ☆114Updated 2 years ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆75Updated 4 months ago
- The code for paper "The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)", exploring the privacy risk o…☆60Updated 10 months ago
- A Synthetic Dataset for Personal Attribute Inference (NeurIPS'24 D&B)☆45Updated 4 months ago
- A toolkit to assess data privacy in LLMs (under development)☆64Updated 11 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆171Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆99Updated last year
- A codebase that makes differentially private training of transformers easy.☆181Updated 2 years ago
- ☆48Updated 9 months ago
- ☆189Updated 2 years ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆151Updated last year
- Training data extraction on GPT-2☆193Updated 2 years ago
- [ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text☆50Updated 10 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆52Updated 3 weeks ago
- Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024 Spotlight]☆109Updated 3 weeks ago
- ☆38Updated 2 years ago
- 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…☆333Updated last year
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆60Updated 2 months ago
- A Comprehensive Assessment of Trustworthiness in GPT Models☆309Updated last year
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆171Updated 11 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆107Updated 10 months ago
- [EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156☆42Updated last year