STAIR-BUPT / JailBench
JailBench:大型语言模型越狱攻击风险评测中文数据集
☆22Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for JailBench
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆159Updated 5 months ago
- SC-Safety: 中文大模型多轮对抗安全基准☆107Updated 8 months ago
- ☆40Updated 6 months ago
- 复旦白泽大模型安全基准测试集(2024年夏季版)☆27Updated 3 months ago
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆77Updated 3 months ago
- ☆93Updated 2 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆61Updated 8 months ago
- ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]☆158Updated last month
- ☆54Updated 3 weeks ago
- 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
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆36Updated 2 months ago
- 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
- Papers about red teaming LLMs and Multimodal models.☆78Updated this week
- 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
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆21Updated 5 months ago
- Figure it out: Analyzing-based Jailbreak Attack on Large Language Models☆16Updated 2 weeks ago
- 基于ChatGPT构建的中文self-instruct数据集☆113Updated last year
- The code and resource of "Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmark"…☆53Updated last month
- "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
- The official dataset of paper "Goal-Oriented Prompt Attack and Safety Evaluation for LLMs".☆15Updated 9 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆26Updated last year
- 【ACL 2024】 SALAD benchmark & MD-Judge☆106Updated last month
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆61Updated 3 months ago
- Agent Security Bench (ASB)☆42Updated 2 weeks ago
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"☆122Updated 9 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆24Updated 3 months ago
- [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise a…☆56Updated last month
- ☆32Updated 6 months ago
- 对llama3进行全参微调、lora微调以及qlora微调。☆153Updated last month
- ☆30Updated 5 months ago