作者位次 #4/6ECCV 2026Poster
Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
Yuan Xiong · Miao Ziqi · Lijun Li · Chen Qian · Jie Li · Jing Shao
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。
Yuan Xiong · Miao Ziqi · Lijun Li · Chen Qian · Jie Li · Jing Shao
Chen Qian · Yimeng Wang · Yu Chen · Lingfei Wu · Andreas Stathopoulos
Explainable AI (XAI) in high-stakes domains should help stakeholders trust and verify system outputs. Yet Chain-of-Thought methods reason before concluding, and logical gaps or hallucinations can yield conclusions that do not reliably align with their rationale. Thus, we propose “Result → Justify...