arXiv AI

What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions

The paper introduces Attnlocate, a runtime framework that localizes behavior‑guiding instructions within the attention matrix of large language model agents. By treating this localization as an object detection task, Attnlocate uses a multi‑head, multi‑layer attention aggregation scheme and a 1‑D U‑Net to identify spans that influence tool‑calling decisions. The system then adjudicates potential malicious invocations based on the authority of the source, achieving high detection metrics across diverse LLM families and demonstrating transferability to unseen models.

arXiv AI
2d ago

Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks

The paper proposes universal, tool‑based defenses for large language model agents that use external tools, addressing four types of adversarial attacks: direct and indirect prompt injection, memory poisoning, and backdoor attacks. Two main defenses are introduced: Attacker Tool Filtering, which uses anomaly detection to remove suspicious tools, and Normal Tool Recalling, which restores the agent’s original toolset before planning. The authors also add prompt‑based defenses such as Chain‑of‑Thought prompting and self‑reflection, and demonstrate that these methods dramatically lower attack success rates—often to 0%—across multiple open‑source and proprietary LLMs while maintaining or improving task performance.

By Xiaoyan Li, Yunli Wang
arXiv AI
Sep 7

Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection

Repeat-After-Me is a black-box adaptive visual prompt injection technique that can reveal personally identifiable information or trigger malicious tool calls in both open-weight and commercial vision‑language models, achieving attack success rates above 80% on Qwen3.6‑27B and 47% on GPT‑5.5. The method works even when the benign user prompt is unrelated to the injected task and does not explicitly authorize it, and it retains significant effectiveness when transferred across models or optimized on surrogate systems. In a real‑world OpenClaw Discord deployment, a minimally injected image can overwrite TOOLS.md, enabling remote code execution and secret exfiltration.

By Sizhe Chen, Yu-Lin Tsai, Ivan Evtimov, Kamalika Chaudhuri, Raluca Ada Popa, David Wagner, Arman Zharmagambetov