Steal the Patch Size: Adversarially Manipulate Vision-Language Models 文章

ArXiv CS.CV2026-07-02PAPERen作者: Kai Hu, Akash Bharadwaj, Weichen Yu, Matt Fredrikson
大语言模型
查看原文 →
关系图谱

Steal the Patch Size: Adversarially Manipulate Vision-Language Models · 相关事件

暂无数据