论文精选

ChainAgent:用 LLM 智能体自动发现 PHP 应用的可组合漏洞链

ChainAgent: Automated Chainable Vulnerability Discovery in PHP Web Applications

精选理由

这是篇安全方向的论文:作者拿 386 条真实攻击链训练出搜索策略,让 LLM 智能体在 PHP 源码里自己找漏洞、自己拼攻击链,找 RCE 的能力比 Codex 强不少。做代码审计、渗透测试或安全研究的读者可以看看它的攻击图方法。

学术团队发布 ChainAgent,一个以目标为导向的 LLM 智能体框架,用于在 PHP Web 应用源码中联合发现漏洞与可被攻击复用的功能组件。该框架基于对 386 条真实 Web 攻击链的实证研究,将漏洞和功能 gadget 用前置条件与安全相关对象的能力来表示,通过不断演化的攻击图双向搜索:从未满足的前置条件反向寻找能力生产者,从已发现能力正向寻找可放大它的功能组件。

正文

评测中,ChainAgent 与通用编码智能体 Codex 在 15 个 PHP 应用、3 个共享 LLM 后端上对比,goal-reaching 组件召回率达 42.02%–44.63%,恢复的正确依赖边数量最多是 Codex 的 4.4 倍。在 30 个真实 PHP 应用的补充评估中,ChainAgent 找出 20 个漏洞和 13 条攻击链,其中 9 条可实现远程代码执行(RCE)。

与先找漏洞、再拼攻击路径的传统方法不同,ChainAgent 把安全相关性只有在攻击链中才显现的未知组件纳入同一搜索过程,这对 PHP 遗留系统的渗透测试与代码审计有直接参考价值。

原文 · arXiv cs.AI

ChainAgent: Automated Chainable Vulnerability Discovery in PHP Web Applications

High-impact attacks on PHP web applications often chain limited-capability vulnerabilities with other flaws or intended behaviors. Discovering these chains requires identifying flaws and the dependencies enabling capability composition. Existing vulnerability discovery techniques analyze flaws in isolation, while attack planning assumes known components. This separation makes it difficult to discover previously unknown components whose security relevance becomes apparent only through their potential roles in an exploit chain. We present ChainAgent, a goal-directed LLM-agent framework that jointly discovers exploit-chain components and their capability dependencies in source code. Guided by an empirical study of 386 real-world web exploit chains, ChainAgent represents vulnerabilities and functional gadgets--intended program behaviors that can be repurposed in attacks--through preconditions and capabilities over security-relevant objects. Instead of discovering vulnerabilities first and constructing attack paths afterward, ChainAgent uses an evolving exploit graph to guide source-code inspection. It searches backward from unmet preconditions for capability producers and forward from discovered capabilities for functional gadgets that consume or amplify them. Object-centered chaining knowledge from our empirical study directs searches toward promising vulnerability classes, functional operations, and object accesses. We evaluate ChainAgent against Codex, a general-purpose coding agent, on 15 PHP applications across three shared LLM backends. ChainAgent achieves 42.02%--44.63% recall for goal-reaching components and recovers up to 4.4 times as many correct goal-reaching dependency edges as Codex. An additional evaluation of 30 real-world PHP applications identifies 20 vulnerabilities and 13 exploit chains, nine of which achieve remote code execution (RCE).

产业坐标与信源核验

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:ChainAgent、Codex、LLM智能体、代码审计,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Xinyi Wang, Yeting Li, Shizhe Cui, Jiaming Guo, Qin Mai, Yecheng Sun, Hengyu Yang, Yujie Sun, Huina Chao, Yang Xiao, Feng Li, Wei Huo),经 AITOP 多维评分管线结构化提炼。