GraySwanAI / nanoGCG
A fast + lightweight implementation of the GCG algorithm in PyTorch
☆72Updated last week
Related projects: ⓘ
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆77Updated 4 months ago
- Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆34Updated 3 weeks ago
- Improving Alignment and Robustness with Circuit Breakers☆124Updated 2 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆110Updated 4 months ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆100Updated 3 months ago
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆27Updated 7 months ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆17Updated 10 months ago
- Python package for measuring memorization in LLMs.☆107Updated this week
- ☆47Updated last year
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆45Updated last month
- An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]☆169Updated last month
- ☆63Updated 10 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆37Updated last month
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆26Updated last month
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆181Updated last month
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆59Updated 6 months ago
- ☆22Updated this week
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆11Updated 4 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆106Updated 6 months ago
- Landing Page for TOFU☆79Updated 3 months ago
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆55Updated 8 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆72Updated 4 months ago
- SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors☆30Updated 2 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆76Updated 3 weeks ago
- A collection of automated evaluators for assessing jailbreak attempts.☆55Updated 2 months ago
- ☆24Updated last month
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆33Updated 3 weeks ago
- Weak-to-Strong Jailbreaking on Large Language Models☆62Updated 6 months ago
- Code to break Llama Guard☆27Updated 9 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆48Updated last week