Security Papers
- ChatGPT for Digital Forensic Investigation: The Good, The Bad, and The Unknown
https://arxiv.org/pdf/2307.10195.pdf
- Can We Generate Shellcodes via Natural Language? An Empirical Study
https://link.springer.com/article/10.1007/s10515-022-00331-3
- Chatbots to ChatGPT in a Cybersecurity Space: Evolution, Vulnerabilities, Attacks, Challenges, and Future Recommendations
https://arxiv.org/pdf/2306.09255.pdf
Security Tools
- LLMFuzzer
简介:LLMFuzzer是用于寻找和利用AI系统漏洞的框架,未来的开发路线是适配各种LLM API、集成不同的模糊测试策略。
链接:https://github.com/mnns/LLMFuzzer
- SecGPT
简介:致力于成为面向网络安全领域的AutoGPT
链接:https://github.com/ZacharyZcR/SecGPT
- AI-goat
简介: 面向带缺陷的LLM的CTF挑战
链接:https://github.com/dhammon/ai-goat
- PsychoEvals
简介: 以MBTI人格评估、提示词注入检测为基础的LLM安全评估轻量框架
链接:https://github.com/NextWordDev/psychoevals
- rebuff
简介: 提示词注入检测工具
链接:https://github.com/protectai/rebuff