论文58
宾州州立大学论文提出 BadEvolve,可向自我进化智能体技能植入后门
原标题:New Penn State paper shows that attackers can make self-evolving AI agents plant backdoors in their own skills just by slipping in poison...
宾州州立大学一篇论文提出 BadEvolve,只需向自我进化智能体的学习集注入 20 个被投毒的训练任务,就能让智能体把攻击者设定的规则写进自己的技能并在后续任务中反复触发。
中文译文尚未完成,先为你展示原文。
New Penn State paper shows that attackers can make self-evolving AI agents plant backdoors in their own skills just by slipping in poisoned training tasks.
Self-evolving agents turn past runs into reusable skills, so a bad rule in a skill keeps firing on future tasks. Earlier attacks assumed direct edits to skills, which rarely holds when the agent writes them itself.
BadEvolve only injects 20 tasks into the agent's learning set, then tunes their wording with an LLM optimizer. It checks where each attempt breaks: whether the rule got written into a skill, loaded, followed, and produced the attacker's goal.
It injected an attacker-chosen payload 79.6% of the time on Kimi-K2.5 across 4 frameworks and 3 benchmarks, versus 37.6% for the best baseline. Clean-task accuracy fell only 1.1 points, so the backdoor is hard to notice.
If your agent learns skills from user-submitted or external tasks, treat those tasks as untrusted and review learned skills before reuse.
– arxiv. org/abs/2611.10542
Title: "When Experience Becomes a Backdoor: Poisoning Self-Evolving LLM Agents via Failure-Aware Task Optimization"
