arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.07287cs.CRcs.SE
收藏

Patch-to-PoC: 对Linux内核N-day漏洞自动复现的系统研究

Patch-to-PoC: A Systematic Study of Agentic LLM Systems for Linux Kernel N-Day Reproduction

University of California, Riverside(加州大学河滨分校)

Juefei Pu, Xingyu Li, Zhengchuan Liang, Jonathan Cox, Yifan Wu, Kareem Shehada, Arrdya Srivastav, Zhiyun Qian

AI总结:

本文提出K-Repro系统,利用LLM自动复现Linux内核N-day漏洞,实现超过50%的漏洞复现率,为自主安全代理的构建和N-day风险评估提供指导。

摘要:

基于自主大型语言模型(LLM)的系统近年来在广泛的安全任务中展示了有前景的结果。然而,目前尚无系统研究其在自主复现Linux内核漏洞并提供具体证明概念(PoCs)方面的有效性。由于Linux内核的规模、复杂性和底层性质,此类任务普遍被认为对当前基于LLM的方法尤其具有挑战性。在本文中,我们首次对基于LLM的Linux内核漏洞复现进行了大规模研究。为此,我们开发了K-Repro,一个具有受控代码浏览、虚拟机管理、交互和调试能力的基于LLM的智能系统。使用内核安全补丁作为输入,K-Repro自动化地复现Linux内核中的N-day漏洞。在从KernelCTF收集的100个真实可利用的Linux内核漏洞数据集中,我们的结果表明,K-Repro可以生成复现超过50%案例的PoC,且具有实际的时间和经济成本。除了总体成功率外,我们还进行了对有效性、效率、稳定性和影响因素的深入研究,以解释何时智能复现成功,何处失败,以及哪些组件驱动性能。这些发现为构建更可靠的自主安全代理以及从进攻和防御角度评估现实中的N-day风险提供了可操作的指导。

英文摘要:

Autonomous large language model (LLM) based systems have recently shown promising results across a range of cybersecurity tasks. However, there is no systematic study on their effectiveness in autonomously reproducing Linux kernel vulnerabilities with concrete proofs-of-concept (PoCs). Owing to the size, complexity, and low-level nature of the Linux kernel, such tasks are widely regarded as particularly challenging for current LLM-based approaches. In this paper, we present the first large-scale study of LLM-based Linux kernel vulnerability reproduction. For this purpose, we develop K-Repro, an LLM-based agentic system equipped with controlled code-browsing, virtual machine management, interaction, and debugging capabilities. Using kernel security patches as input, K-Repro automates end-to-end bug reproduction of N-day vulnerabilities in the Linux kernel. On a dataset of 100 real-world exploitable Linux kernel vulnerabilities collected from KernelCTF, our results show that K-Repro can generate PoCs that reproduce over 50\% of the cases with practical time and monetary cost. Beyond aggregate success rates, we perform an extensive study of effectiveness, efficiency, stability, and impact factors to explain when agentic reproduction succeeds, where it fails, and which components drive performance. These findings provide actionable guidance for building more reliable autonomous security agents and for assessing real-world N-day risk from both offensive and defensive perspectives.

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。

↑