AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models 文章

ArXiv CS.CV2026-07-08PAPERen作者: Yuanmin Huang, Zhenfei Zhang, Mi Zhang, Geng Hong, Qinqin He, Jialing Tao, Hui Xue, Min Yang
查看原文 →
关系图谱

AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models · 相关事件

暂无数据