作者位次 #6/9ICML 2026Poster· Deep Learning / Robustness
SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
Yunhao Feng · Yifan Ding · Yingshui Tan · Boren Zheng · Xiaolong Li · Kun Zhai · Yishan Li · Yanming Guo · Wenke Huang
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Yunhao Feng · Yifan Ding · Yingshui Tan · Boren Zheng · Xiaolong Li · Kun Zhai · Yishan Li · Yanming Guo · Wenke Huang
Yunhao Feng · Yige Li · Yutao Wu · Yingshui Tan · Yanming Guo · Yifan Ding · Kun Zhai · Xingjun Ma · Yu-Gang Jiang
Large language model (LLM) agents execute tasks through multi-step workflows that combine planning, memory, and tool use. While this design enables autonomy, it also expands the attack surface for backdoor threats. Backdoor triggers injected into specific stages of an agent workflow can persist t...