When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dingeto, Hiskias, Kwon, Taeyoun, Choi, Dasol, Kim, Bodam, Lee, DongGeon, Park, Haon, Lee, JaeHoon, Shin, Jongho
Format:	Preprint
Published:	2025
Subjects:	Sound Artificial Intelligence Cryptography and Security Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.03365