Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Yukun, Li, Mingjie, Backes, Michael, Zhang, Yang
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.21189