FORGE:对深度研究智能体的研究轨迹劫持攻击
FORGE: Research-Trajectory Hijacking Attacks on Deep Research Agents
AI总结:
研究针对深度研究智能体,利用其工作流程中的规划层中毒面,提出FORGE两级攻击劫持子任务规划,还引入PRISM指标和Root Query Anchoring防御,展示攻击效果及防御作用。
摘要:
深度研究智能体将开放式查询分解为子任务,多轮检索网络证据并合成长篇报告。此工作流程产生规划层中毒面,对抗性文档可操纵后续问题。我们提出FORGE,一种两级攻击,结合文档内推理伪造与文档间链协调来劫持子任务规划。还介绍PRISM指标和Root Query Anchoring轻量级防御。
英文摘要:
Deep research agents decompose open-ended queries into subtasks, retrieve web evidence over multiple rounds, and synthesize long-form reports. This workflow creates a planning-layer poisoning surface: adversarial documents that enter the retrieval pool can steer follow-up questions and turn a local injection into report-level contamination. We present FORGE (Fabricated Orchestrated Reasoning chain for aGent Exploitation), a two-level attack that combines intra-document reasoning fabrication with inter-document chain coordination to hijack subtask planning. We further introduce the PRISM metric, which weights infected report claims by cognitive type, and Root Query Anchoring, a lightweight defense that ties recursive follow-up generation to the root query. Across 25 queries, Network FORGE reaches 26.4% PRISM with five injected documents and exhibits depth migration, in which recursive synthesis shifts poisoned content from overt framing into factual premises. On the 10-query defense subset, RQA (Root Query Anchoring) reduces PRISM from 38.5% to 18.3%.
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。