Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hong, Wenjing, Rong, Zhonghua, Wang, Li, Chang, Feng, Zhu, Jian, Tang, Ke, Zhu, Zexuan, Ong, Yew-Soon
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.20122