arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.13574cs.SEcs.CR
收藏

面向执行状态的LLM推理用于自动化漏洞证明生成

Execution-State-Aware LLM Reasoning for Automated Proof-of-Vulnerability Generation

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Haoyu Li, Xijia Che, Yanhao Wang, Xiaojing Liao, Luyi Xing

AI总结:

DrillAgent通过结合LLM语义推理与执行状态反馈,实现自动化漏洞证明生成,显著提升漏洞检测效率。

摘要:

漏洞证明生成是软件安全中的关键任务,是漏洞验证、假阳性减少和补丁验证的基石。尽管定向模糊测试能有效驱动路径探索,但满足复杂的语义约束仍然是自动化漏洞生成中的持久瓶颈。大型语言模型(LLMs)凭借其语义推理能力提供了一种有前景的替代方案;然而,现有基于LLM的方法缺乏对具体执行行为的充分支撑,限制了其生成精确漏洞证明的能力。本文提出了DrillAgent,一个代理框架,将漏洞证明生成重新表述为迭代的假设验证-细化过程。为弥合静态推理与动态执行之间的差距,DrillAgent结合LLM的语义推断与程序状态的反馈。代理分析目标代码以推测输入,观察执行行为,并采用一种新的机制将低级执行跟踪转换为源级约束。这种闭环设计使代理能够逐步使其输入生成与漏洞的精确要求对齐。我们评估了DrillAgent在SEC-bench上的表现,这是一个大规模的真实世界C/C++漏洞基准测试集。实验结果表明,DrillAgent在固定预算约束下显著优于最先进的LLM代理基线,解决的CVE任务数量比最佳基线多达52.8%。这些结果突显了在复杂软件系统中对执行状态的推理需求,以实现可靠的漏洞证明生成。

英文摘要:

Proof-of-Vulnerability (PoV) generation is a critical task in software security, serving as a cornerstone for vulnerability validation, false positive reduction, and patch verification. While directed fuzzing effectively drives path exploration, satisfying complex semantic constraints remains a persistent bottleneck in automated exploit generation. Large Language Models (LLMs) offer a promising alternative with their semantic reasoning capabilities; however, existing LLM-based approaches lack sufficient grounding in concrete execution behavior, limiting their ability to generate precise PoVs. In this paper, we present DrillAgent, an agentic framework that reformulates PoV generation as an iterative hypothesis-verification-refinement process. To bridge the gap between static reasoning and dynamic execution, DrillAgent synergizes LLM-based semantic inference with feedback from concrete program states. The agent analyzes the target code to hypothesize inputs, observes execution behavior, and employs a novel mechanism to translate low-level execution traces into source-level constraints. This closed-loop design enables the agent to incrementally align its input generation with the precise requirements of the vulnerability. We evaluate DrillAgent on SEC-bench, a large-scale benchmark of real-world C/C++ vulnerabilities. Experimental results show that DrillAgent substantially outperforms state-of-the-art LLM agent baselines under fixed budget constraints, solving up to 52.8% more CVE tasks than the best-performing baseline. These results highlight the necessity of execution-state-aware reasoning for reliable PoV generation in complex software systems.

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。

↑