第4期 - GPTSecurity周报

GPTSecurity是一个涵盖了前沿学术研究和实践经验分享的社区，集成了生成预训练 Transformer（GPT）、人工智能生成内容（AIGC）以及大型语言模型（LLM）等安全领域应用的知识。在这里，您可以找到关于GPT/AIGC/LLM最新的研究论文、博客文章、实用的工具和预设指令（Prompts）。现为了更好的知悉近一周的贡献内容，现总结如下如下。

Security Papers

1 GPT自身安全

• A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation
• https://arxiv.org/pdf/2305.11391.pdf

• Taxonomy of Risks posed by Language Models
• https://dl.acm.org/doi/10.1145/3531146.3533088

2 威胁检测

• FlowTransformer: A Transformer Framework for Flow-based Network Intrusion Detection Systems
• https://arxiv.org/pdf/2304.14746.pdf

3 软件供应链安全

• CODAMOSA: Escaping Coverage Plateaus in Test Generation with Pre-trained Large Language Models
• 微软在ICSE2023上发布的论文，旨在利用LLM来缓解传统fuzz中的陷入“Coverage Plateaus”的问题
• https://www.carolemieux.com/codamosa_icse23.pdf

• BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT
• https://www.ndss-symposium.org/wp-content/uploads/2023/02/NDSS2023Poster_paper_7966.pdf