Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Yu-Hang, Xiong, Yu-Jie, Zhang, Hao, Zhang, Jia-Chen, Zhou, Zheng
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security 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/2504.05652