Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models 文章

ArXiv CS.CV2026-06-05NEWSen作者: Liangsheng Liu, Si Chen, Jiamin Wu, Weiwei Feng, Zhixin Cheng, Xiaotian Yin, Wenfei Yang, Tianzhu Zhang
查看原文 →
关系图谱

Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models · 相关人物

暂无数据