GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xie, Yueqi, Fang, Minghong, Pi, Renjie, Gong, Neil
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!

Internet

https://arxiv.org/abs/2402.13494