一作ICML 2026Poster· Social Aspects / Security
Budget-Efficient Attacks and Robustness Training for Cooperative MARL
Junyong Jiang · Xin Yuan · Longhe Lin · Songze Li · Lu Dong
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。
Junyong Jiang · Xin Yuan · Longhe Lin · Songze Li · Lu Dong
Chenxing Xu · Junyong Jiang · Zehu Zhang · Lu Dong
Large Visual Language Models (LVLMs) achieve superior multimodal reasoning but inevitably expand the safety attack surface. While recent studies have explored emoji-based vulnerabilities, they predominantly focus on textual tokenization artifacts and neglect the model’s intrinsic capability to in...