STAIR-BUPT / JailBench

Related projects ⓘ

Alternatives and complementary repositories for JailBench

• thu-coai / SafetyBench
  Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]
  ☆159Updated 5 months ago
• CLUEbenchmark / SuperCLUE-Safety
  SC-Safety: 中文大模型多轮对抗安全基准
  ☆107Updated 8 months ago
• Aatrox103 / SAP
  ☆40Updated 6 months ago
• WhitzardIndex / WhitzardBench-2024A
  复旦白泽大模型安全基准测试集（2024年夏季版）
  ☆27Updated 3 months ago
• niconi19 / LLM-Conversation-Safety
  [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
  ☆77Updated 3 months ago
• Allen-piexl / JailbreakZoo
  ☆93Updated 2 months ago
• DAMO-NLP-SG / multilingual-safety-for-LLMs
  [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"
  ☆61Updated 8 months ago
• thu-coai / ShieldLM
  ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]
  ☆158Updated last month
• renqibing / ActorAttack
  ☆54Updated 3 weeks ago
• AIFlames / Flames
  Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.
  ☆33Updated 6 months ago
• xirui-li / DrAttack
  Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
  ☆36Updated 2 months ago
• RockyHHH / Safety-Evaluating
  本文提出了一个基于“文心一言”的中国LLMs的安全评估基准，其中包括8种典型的安全场景和6种指令攻击类型。此外，本文还提出了安全评估的框架和过程，利用手动编写和收集开源数据的测试Prompts，以及人工干预结合利用LLM强大的评估能力作为“共同评估者”。
  ☆20Updated last year
• Libr-AI / OpenRedTeaming
  Papers about red teaming LLMs and Multimodal models.
  ☆78Updated this week
• NJUNLP / ReNeLLM
  The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…
  ☆74Updated 4 months ago
• YancyKahn / CoA
  Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM
  ☆21Updated 5 months ago
• theshi-1128 / ABJ-Attack
  Figure it out: Analyzing-based Jailbreak Attack on Large Language Models
  ☆16Updated 2 weeks ago
• wptoux / self-instruct-zh
  基于ChatGPT构建的中文self-instruct数据集
  ☆113Updated last year
• DUT-lujunyu / ToxiCN
  The code and resource of "Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmark"…
  ☆53Updated last month
• whitzard-ai / jade-db
  "他山之石、可以攻玉"：复旦白泽智能发布面向国内开源和国外商用大模型的Demo数据集JADE-DB
  ☆313Updated last week
• liuchengyuan123 / CPAD
  The official dataset of paper "Goal-Oriented Prompt Attack and Safety Evaluation for LLMs".
  ☆15Updated 9 months ago
• HKUST-KnowComp / LLM-Multistep-Jailbreak
  Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT
  ☆26Updated last year
• OpenSafetyLab / SALAD-BENCH
  【ACL 2024】 SALAD benchmark & MD-Judge
  ☆106Updated last month
• BillChan226 / AgentPoison
  [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
  ☆61Updated 3 months ago
• agiresearch / ASB
  Agent Security Bench (ASB)
  ☆42Updated 2 weeks ago
• tmlr-group / DeepInception
  [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"
  ☆122Updated 9 months ago
• YihanWang617 / LLM-Jailbreaking-Defense-Backtranslation
  Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"
  ☆24Updated 3 months ago
• LLM-DRA / DRA
  [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise a…
  ☆56Updated last month
• qiuhuachuan / latent-jailbreak
  ☆32Updated 6 months ago
• taishan1994 / Llama3.1-Finetuning
  对llama3进行全参微调、lora微调以及qlora微调。
  ☆153Updated last month
• ydyjya / LLM-IHS-Explanation
  ☆30Updated 5 months ago