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 2604.07536cs.CR
收藏

TRUSTDESC: 通过可信描述生成防止LLM应用中的工具污染

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

The Pennsylvania State University(宾夕法尼亚州立大学)

Hengkai Ye, Zhechang Zhang, Jinyuan Jia, Hong Hu

AI总结:

TRUSTDESC通过生成可信工具描述防止LLM中的工具污染攻击,采用三阶段流程提取代码片段、生成描述并动态验证,提升任务完成率并抑制隐式攻击。

摘要:

大型语言模型(LLMs)越来越多地依赖外部工具执行时间敏感任务和现实世界操作。尽管工具集成扩展了LLM的能力,但也引入了新的提示注入攻击面:工具污染攻击(TPAs)。攻击者通过嵌入恶意指令(显式TPA)或误导性声明(隐式TPA)来操控工具描述,影响模型行为和工具选择。现有防御措施主要检测异常指令,对隐式TPA效果有限。本文提出了TRUSTDESC,首个通过自动从实现中生成可信工具描述来防止工具污染的框架。TRUSTDESC通过三阶段流程生成实现忠实的描述。SliceMin通过可达性感知的静态分析和LLM引导的去膨胀提取最小的工具相关代码片段。DescGen从这些片段中合成描述并减轻误导或对抗性代码特征。DynVer通过动态验证执行合成任务并验证行为声明。我们在52个真实世界工具上评估TRUSTDESC,覆盖多个工具生态系统。结果表明,TRUSTDESC生成的准确工具描述提高了任务完成率,同时在根源上抑制隐式TPA,且时间与货币成本极低。

英文摘要:

Large language models (LLMs) increasingly rely on external tools to perform time-sensitive tasks and real-world actions. While tool integration expands LLM capabilities, it also introduces a new prompt-injection attack surface: tool poisoning attacks (TPAs). Attackers manipulate tool descriptions by embedding malicious instructions (explicit TPAs) or misleading claims (implicit TPAs) to influence model behavior and tool selection. Existing defenses mainly detect anomalous instructions and remain ineffective against implicit TPAs. In this paper, we present TRUSTDESC, the first framework for preventing tool poisoning by automatically generating trusted tool descriptions from implementations. TRUSTDESC derives implementation-faithful descriptions through a three-stage pipeline. SliceMin performs reachability-aware static analysis and LLM-guided debloating to extract minimal tool-relevant code slices. DescGen synthesizes descriptions from these slices while mitigating misleading or adversarial code artifacts. DynVer refines descriptions through dynamic verification by executing synthesized tasks and validating behavioral claims. We evaluate TRUSTDESC on 52 real-world tools across multiple tool ecosystems. Results show that TRUSTDESC produces accurate tool descriptions that improve task completion rates while mitigating implicit TPAs at their root, with minimal time and monetary overhead.

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。

↑