← 研踪 PaperTrailarXiv:2611.04393 · v1
Voluntary Servitude: Weaponized Safety Warning Mechanisms for Controlling AI Agents
首次提交 2026-11-03 14:26
版本更新 2026-11-03 14:26
雷达观测 2026-11-04 23:40
摘要
LLM agents increasingly act on information retrieved from public sources they treat as credible, which turns a manipulated recommendation into a transaction, a dependency, or a decision with physical consequences. The security literature models this threat as instruction injection, in which an adversary writes a command into retrieved content and deployed defenses learn to recognize command syntax. We show that an attacker can instead steer an agent through the agent's own harm-avoidance. A single fabricated hazard, written as an ordinary review, leads the agent to disqualify the legitimate options and select the attacker's target by its own reasoning, with no command for a detector to recognize. We call this voluntary servitude. These payloads steer agents about as often as instruction injection (60.4% vs. 66.0%), and deployed injection detectors score them as benign, so behind a filter they are 1.7-4.4x more effective. We measure this at the generation stage across six models and ten consumer-service domains, for three attack families, and show that it transfers to production browser agents, outperforming instruction injection, and to a retrieval pipeline (1.0-57.0% end-to-end success, depending on the retriever). We then show that a corroboration requirement added to the agent's instructions removes roughly 95% of the exposure against a non-adaptive attacker without retraining. With the requirement in place, the agent still reads the planted hazard and no longer acts on it.
作者备注：Accepted at NeurIPS 2026 (Main Track). 17 pages, 7 figures, 8 tables
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-03 14:26 · 最新观测版本
Voluntary Servitude: Weaponized Safety Warning Mechanisms for Controlling AI Agents
LLM agents increasingly act on information retrieved from public sources they treat as credible, which turns a manipulated recommendation into a transaction, a dependency, or a decision with physical consequences. The security literature models this threat as instruction injection, in which an adversary writes a command into retrieved content and deployed defenses learn to recognize command syntax. We show that an attacker can instead steer an agent through the agent's own harm-avoidance. A single fabricated hazard, written as an ordinary review, leads the agent to disqualify the legitimate options and select the attacker's target by its own reasoning, with no command for a detector to recognize. We call this voluntary servitude. These payloads steer agents about as often as instruction injection (60.4% vs. 66.0%), and deployed injection detectors score them as benign, so behind a filter they are 1.7-4.4x more effective. We measure this at the generation stage across six models and ten consumer-service domains, for three attack families, and show that it transfers to production browser agents, outperforming instruction injection, and to a retrieval pipeline (1.0-57.0% end-to-end success, depending on the retriever). We then show that a corroboration requirement added to the agent's instructions removes roughly 95% of the exposure against a non-adaptive attacker without retraining. With the requirement in place, the agent still reads the planted hazard and no longer acts on it.
查看此版本解读 →查看此版本原文 ↗