A robust adversarial attack against speech recognition with UAP

Speech recognition (SR) systems based on deep neural networks are increasingly widespread in smart devices. However, they are vulnerable to human-imperceptible adversarial attacks, which cause the SR to generate incorrect or targeted adversarial commands. Meanwhile, audio adversarial attacks are par...

Full description

Bibliographic Details

Published in:	High-Confidence Computing
Main Authors:	Ziheng Qin, Xianglong Zhang, Shujun Li
Format:	Article
Language:	English
Published:	Elsevier 2023-03-01
Subjects:	Machine learning security Audio adversarial attack
Online Access:	http://www.sciencedirect.com/science/article/pii/S2667295222000502