iamgroot42 / mimir
Python package for measuring memorization in LLMs.
☆152Updated 5 months ago
Alternatives and similar repositories for mimir:
Users that are interested in mimir are comparing it to the libraries listed below
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆95Updated 2 months ago
- Code for watermarking language models☆78Updated 7 months ago
- A toolkit to assess data privacy in LLMs (under development)☆57Updated 3 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆80Updated 11 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆129Updated 9 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆86Updated 11 months ago
- Official Repository for Dataset Inference for LLMs☆33Updated 9 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆152Updated 11 months ago
- Improving Alignment and Robustness with Circuit Breakers☆197Updated 7 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆62Updated 5 months ago
- ☆54Updated 2 years ago
- ☆42Updated 2 months ago
- ☆97Updated last year
- A Synthetic Dataset for Personal Attribute Inference (NeurIPS'24 D&B)☆40Updated 4 months ago
- Differentially-private transformers using HuggingFace and Opacus☆136Updated 7 months ago
- A survey of privacy problems in Large Language Models (LLMs). Contains summary of the corresponding paper along with relevant code☆67Updated 10 months ago
- A one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE and is an easily extensible framework for new datase…☆218Updated last week
- A survey on harmful fine-tuning attack for large language model☆161Updated last week
- LLM Unlearning☆153Updated last year
- ☆57Updated 9 months ago
- ☆129Updated 3 weeks ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆51Updated 6 months ago
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆37Updated last year
- Official repository for "PostMark: A Robust Blackbox Watermark for Large Language Models"☆24Updated 7 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆51Updated last month
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆68Updated last year
- Training data extraction on GPT-2☆185Updated 2 years ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆97Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆91Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆76Updated 3 weeks ago