GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yunqiang, Na, Hengyuan, Wu, Di, Hu, Miao, Quan, Guocong
Format:	Preprint
Published:	2026
Subjects:	Sound Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.09222