作者位次 #5/7ICML 2026Poster· Social Aspects / Security
Dissecting the Safety Circuit: Neuronal Intervention for Transferable Adversarial Attacks on VLMs
Chunlong Xie · Kangjie Chen · Shangwei Guo · Shudong Zhang · Jiamou Liu · Tianwei Zhang · Tao Xiang
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。
Chunlong Xie · Kangjie Chen · Shangwei Guo · Shudong Zhang · Jiamou Liu · Tianwei Zhang · Tao Xiang
Xianda Zheng · Zijian Huang · Meng-Fen Chiang · Jiamou Liu · Yuan Fang · Michael J. Witbrock · Kaiqi Zhao
Explicit knowledge conflicts, where retrieved contexts contain contradictory information, have become increasingly prevalent as Large Language Models (LLMs) integrate diverse data sources. The core challenge lies in the complexity of entangled narratives and the heterogeneity of conflict cases, w...