LLM Agents can Autonomously Exploit One-day Vulnerabilities

arXiv:2404.08144v1 Announce Type: new
Abstract: LLMs have becoming increasingly powerful, both in their benign and malicious uses. With the increase in capabilities, researchers have been increasingly interested in their ability to exploit cybersecurity vulnerabilities. In particular, recent work has conducted preliminary studies on the ability of LLM agents to autonomously hack websites. However, these studies are limited to simple vulnerabilities.
In this work, we show that LLM agents can autonomously exploit one-day vulnerabilities in real-world systems. To show this, we …

agents arxiv can capabilities cs.ai cs.cr cybersecurity cybersecurity vulnerabilities exploit hack llm llms malicious researchers studies vulnerabilities websites work