← 研踪 PaperTrailarXiv:2611.04673 · v1
Right Tool, Wrong Parameters: Defending LLM Agents Against Parameter Poisoning
首次提交 2026-11-03 18:57
版本更新 2026-11-03 18:57
雷达观测 2026-11-04 23:39
摘要
Indirect Prompt Injection (IPI) poses a critical threat to LLM agents. Existing defenses largely focus on whether an injection induces a new tool invocation or unintended action. In this paper, we study a different attack surface, parameter poisoning, where the attacker preserves the intended action but manipulates one or more tool arguments, such as a recipient or other task-critical value. Such attacks are difficult to detect because no new action is introduced, while parameter changes themselves are often legitimate parts of the user's request. Our key insight is that the legitimacy of a parameter change should be determined by the trust of the information flow that produces it under the user query. The query induces a task-specific trust hierarchy over available information fields: some are trusted to determine particular parameters, while others should have little or no influence. Based on this insight, we propose AuthorityFlow, a three-stage parameter-level defense. First, it interprets the user query to construct a task-specific trust hierarchy over the information fields available to the agent. Second, for each tool argument, it traces the information flow that produces its current value and attributes the value to its supporting field. Finally, it accepts the value only when that field is trusted to determine the parameter under the current task, allowing high-trust changes while flagging low-trust influence as potential parameter poisoning. We further introduce FactAuthBench for evaluating parameter poisoning in LLM agents. Without defense, the attack success rate reaches 93.06%. AuthorityFlow reduces it to 9.03%, while retaining 82.64% benign task utility compared with 90.28% without defense. Our results show that effective IPI defense requires reasoning not only about what action an agent takes, but also about which information is trusted to determine its parameters.
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 18:57 · 最新观测版本
Right Tool, Wrong Parameters: Defending LLM Agents Against Parameter Poisoning
Indirect Prompt Injection (IPI) poses a critical threat to LLM agents. Existing defenses largely focus on whether an injection induces a new tool invocation or unintended action. In this paper, we study a different attack surface, parameter poisoning, where the attacker preserves the intended action but manipulates one or more tool arguments, such as a recipient or other task-critical value. Such attacks are difficult to detect because no new action is introduced, while parameter changes themselves are often legitimate parts of the user's request. Our key insight is that the legitimacy of a parameter change should be determined by the trust of the information flow that produces it under the user query. The query induces a task-specific trust hierarchy over available information fields: some are trusted to determine particular parameters, while others should have little or no influence. Based on this insight, we propose AuthorityFlow, a three-stage parameter-level defense. First, it interprets the user query to construct a task-specific trust hierarchy over the information fields available to the agent. Second, for each tool argument, it traces the information flow that produces its current value and attributes the value to its supporting field. Finally, it accepts the value only when that field is trusted to determine the parameter under the current task, allowing high-trust changes while flagging low-trust influence as potential parameter poisoning. We further introduce FactAuthBench for evaluating parameter poisoning in LLM agents. Without defense, the attack success rate reaches 93.06%. AuthorityFlow reduces it to 9.03%, while retaining 82.64% benign task utility compared with 90.28% without defense. Our results show that effective IPI defense requires reasoning not only about what action an agent takes, but also about which information is trusted to determine its parameters.
查看此版本解读 →查看此版本原文 ↗