XHMY / AutoDefense
AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
☆23Updated 3 months ago
Related projects: ⓘ
- Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆36Updated last month
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆125Updated 2 weeks ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆181Updated last month
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆84Updated this week
- ☆33Updated 2 months ago
- An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]☆169Updated last month
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆45Updated last month
- Papers about red teaming LLMs and Multimodal models.☆66Updated this week
- TAP: An automated jailbreaking method for black-box LLMs☆106Updated 6 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆48Updated last week
- LLM security and privacy☆38Updated 5 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆89Updated 2 months ago
- A collection of automated evaluators for assessing jailbreak attempts.☆55Updated 2 months ago
- The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".☆203Updated last month
- ☆22Updated 7 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆27Updated 5 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking.☆38Updated last month
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆27Updated 7 months ago
- ☆143Updated 9 months ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆76Updated 6 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆110Updated 4 months ago
- Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆76Updated 4 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆72Updated 4 months ago
- ☆17Updated 8 months ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆81Updated 6 months ago
- Fine-tuning base models to build robust task-specific models☆23Updated 5 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
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆57Updated 6 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆33Updated 3 weeks ago
- [ICML2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆78Updated 5 months ago