Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yuanhe, Xie, Fangzhou, Zhou, Zhenhong, Li, Zherui, Chen, Hao, Wang, Kun, Guo, Yufei
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2507.19227