StructuralSleight: Automated Jailbreak Attacks on Large Language Models Utilizing Uncommon Text-Organization Structures

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Bangxin, Xing, Hengrui, Tian, Cong, Huang, Chao, Qian, Jin, Xiao, Huangqing, Feng, Linfeng
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Similar Items