Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Meng, Wang, Kun, Lu, Li, Zhang, Jiaheng, Zhang, Tianwei
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.14604