UM

Browse/Search Results:  1-1 of 1 Help

Selected(0)Clear Items/Page:    Sort:
PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions Conference paper
Zhang, Yudong, Xie, Ruobing, Chen, Jiansheng, Sun, Xingwu, Wang, Yu. PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions[C], New York, NY, USA:Association for Computing Machinery, Inc, 2024, 11175-11183.
Authors:  Zhang, Yudong;  Xie, Ruobing;  Chen, Jiansheng;  Sun, Xingwu;  Wang, Yu
Favorite | TC[Scopus]:0 | Submit date:2024/12/05
Detecting Adversarial Example  Large Vision-language Model