theshi-1128 / jailbreak-benchLinks
The most comprehensive and accurate LLM jailbreak attack benchmark by far
☆19Updated 2 months ago
Alternatives and similar repositories for jailbreak-bench
Users that are interested in jailbreak-bench are comparing it to the libraries listed below
Sorting:
- ☆54Updated 2 weeks ago
- ☆33Updated 8 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆52Updated 9 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆33Updated last year
- ☆80Updated last year
- BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models☆151Updated 2 weeks ago
- ☆57Updated 5 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆141Updated 3 months ago
- An easy-to-use Python framework to defend against jailbreak prompts.☆21Updated 2 months ago
- ☆18Updated 11 months ago
- ☆28Updated 7 months ago
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models☆155Updated 3 months ago
- Safety at Scale: A Comprehensive Survey of Large Model Safety☆160Updated 3 months ago
- ☆86Updated 4 months ago
- LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models☆20Updated last week
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆31Updated 4 months ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆35Updated 10 months ago
- ☆16Updated last week
- 🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access☆29Updated this week
- ☆45Updated last year
- Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)☆36Updated this week
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆126Updated last month
- [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.☆23Updated 10 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆135Updated 6 months ago
- Code Implementation For Paper "FP-VEC: Fingerprinting Large Language Models via Efficient Vector Addition"☆11Updated 7 months ago
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models☆222Updated last year
- ☆26Updated 2 weeks ago
- MASTERKEY is a framework designed to explore and exploit vulnerabilities in large language model chatbots by automating jailbreak attacks…☆22Updated 8 months ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆27Updated 5 months ago
- Accepted by ECCV 2024☆130Updated 7 months ago