LightDefense: A Lightweight Uncertainty-Driven Defense against Jailbreaks via Shifted Token Distribution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Zhuoran, Zhang, Yanyong
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computers and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2504.01533