arXiv:2603.13950v2 cs.CL

ToolFlood: Beyond Selection -- Hiding Valid Tools from LLM Agents via Semantic Covering

Hussein Jawad, Nicolas J-B Brunel

제출 2026-11-18

원문 초록

Large Language Model (LLM) agents increasingly use external tools for complex tasks and rely on embedding-based retrieval to select a small top-$k$ subset for reasoning. Prior work on attacking these systems competes for tool selection, assuming benign tools remain in the retrieved set; the robustness of the retrieval stage that produces this set is underexplored. This paper introduces ToolFlood, a retrieval-layer attack on tool-augmented LLM agents. Rather than altering which tool is chosen after retrieval, ToolFlood attacks retrieval itself: it injects a few attacker-controlled tools whose metadata is positioned to exploit the geometry of embedding space, so that these tools semantically span many user queries, dominate the top-k results, and push all benign tools out of the agent's context. ToolFlood uses a two-phase adversarial tool generation strategy. It first samples subsets of target queries and uses an LLM to iteratively generate diverse tool names and descriptions. It then runs an iterative greedy selection that chooses tools maximizing coverage of remaining queries in embedding space under a cosine-distance threshold, stopping when all queries are covered or a budget is reached. We provide theoretical intuition of retrieval saturation and show on a large catalog (ToolBench) that ToolFlood achieves up to a 95\% attack success rate with a ~1\% injection rate. The code is available at: https://github.com/as1-prog/ToolFlood

제출 이력

확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.

  1. arXiv:2603.13950v2제출 시각 미확인

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

공통 태그로 연결된 공개 논문이 아직 없습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.