论文

Origin 工具帮助安全人员回溯智能体应用的入侵入口

Backtracking Agent Applications Security Incidents

精选理由

智能体应用被攻击后想找到入侵入口很难,日志和代码是两层语义。这篇论文的 Origin 用跨层依赖图把两边连起来,在 5 个应用、8 起事件里全部找对入口。做智能体安全运营和红蓝对抗的工程师可以认真读一读。

arXiv 论文介绍 Origin,一个针对智能体应用安全事件回溯的工具,用于定位 CEP(入侵入口点)。现有回溯依赖的轨迹日志处在智能体功能抽象层,而 CEP 候选是应用代码执行层的函数调用,两层之间存在语义鸿沟,分析师需要逐个检查候选代码。

正文

Origin 通过跨层依赖图(CLDG)把语义层的 region 推断函数连接到底层污点传播子图中的变量,并配套查询语言和 region 推断算法。在五个主流智能体应用、八起攻击事件的案例研究中,使用 Origin 的分析师全部正确识别了 CEP。

原文 · arXiv cs.AI

Backtracking Agent Applications Security Incidents

Agent applications are increasingly deployed, yet agent-specific attacks pose real threats to them. Upon a security incident, organizations backtrack to identify the CEP (compromise entry point), remediate the damage, and prevent its recurrence. The main artifacts available for backtracking are trajectory logs, which record agent functionalities, and source code; app(lication)-specific function call logs are often fairly limited. However, trajectory logs are at the agent functionality abstraction layer, while the CEP candidates are function calls at the app code execution layer. Due to this semantic gap, the analyst needs to manually inspect the relevant code for each CEP candidate to infer its corresponding agent functionality. In this work, we present Origin, a backtracking tool for the analyst to submit a small number of queries to identify CEPs that existing tools cannot provide. Our approach poses two challenges: (1) define the intermediate abstraction that captures the mapping relationships between the two semantic layers; (2) determine the region-to-variable mapping for constructing the cross-layer graph defined in the intermediate abstraction. Each region is a specific group of agent functionalities. Origin addresses the challenges by (1) the cross-layer dependency graph (CLDG) that connects region-inferred functions at the semantic level to the variables in the low-level taint propagation subgraph, plus the associated query language, and (2) the region inference algorithm. Case studies on five popular agent applications across eight attack incidents show that an analyst using Origin correctly identifies all the CEPs.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。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:Origin、智能体、AI安全、污点分析,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」(@Yicheng Cai, Taegyu Kim, Peng Liu),经 AITOP 多维评分管线结构化提炼。