BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Yulin, Li, Haoran, Zhang, Yirui, Zheng, Zihao, Song, Yangqiu, Hooi, Bryan
Format:	Preprint
Published:	2024
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/2408.09093