LLM Agent团队可以利用零日漏洞
Teams of LLM Agents can Exploit Zero-Day Vulnerabilities
AI总结：
针对LLM Agent单独利用零日漏洞时长期规划能力不足的问题，提出HPTSA多Agent系统，通过规划Agent调度子Agent协同工作，在14个真实漏洞基准上较现有框架提升达4.3倍。
摘要：
LLM Agent在网络安全领域变得日益复杂。研究人员已经证明，当给定漏洞描述和玩具级夺旗问题时，LLM Agent可以利用现实世界的漏洞。然而，这些Agent在利用Agent事先未知的现实世界漏洞（零日漏洞）时仍然表现不佳。在这项工作中，我们展示了LLM Agent团队可以利用现实世界的零日漏洞。单独使用时，先前的Agent在探索许多不同的漏洞和长期规划方面存在困难。为了解决这个问题，我们引入了HPTSA，这是一个由可以启动子Agent的规划Agent组成的Agent系统。规划Agent探索系统并决定调用哪些子Agent，解决了在尝试不同漏洞时的长期规划问题。我们构建了一个包含14个现实世界漏洞的基准，并表明我们的Agent团队比先前的Agent框架提高了多达4.3倍。
英文摘要：
LLM agents have become increasingly sophisticated, especially in the realm of cybersecurity. Researchers have shown that LLM agents can exploit real-world vulnerabilities when given a description of the vulnerability and toy capture-the-flag problems. However, these agents still perform poorly on real-world vulnerabilities that are unknown to the agent ahead of time (zero-day vulnerabilities). In this work, we show that teams of LLM agents can exploit real-world, zero-day vulnerabilities. Prior agents struggle with exploring many different vulnerabilities and long-range planning when used alone. To resolve this, we introduce HPTSA, a system of agents with a planning agent that can launch subagents. The planning agent explores the system and determines which subagents to call, resolving long-term planning issues when trying different vulnerabilities. We construct a benchmark of 14 real-world vulnerabilities and show that our team of agents improve over prior agent frameworks by up to 4.3X.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
