Dynamic Optimization and Safety Indicator Injection for Jailbreaking Text-to-Image Models with Multimodal Safety Filters

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Zixuan, Lin, Hao, Xu, Ke, Jiang, Xinghao, Sun, Tanfeng
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2505.18979