CommanderUAP: a practical and transferable universal adversarial attacks on speech recognition models

Abstract Most of the adversarial attacks against speech recognition systems focus on specific adversarial perturbations, which are generated by adversaries for each normal example to achieve the attack. Universal adversarial perturbations (UAPs), which are independent of the examples, have recently...

Full description

Bibliographic Details

Published in:	Cybersecurity
Main Authors:	Zheng Sun, Jinxiao Zhao, Feng Guo, Yuxuan Chen, Lei Ju
Format:	Article
Language:	English
Published:	SpringerOpen 2024-06-01
Subjects:	Adversarial examples Universal adversarial perturbations Speech recognition
Online Access:	https://doi.org/10.1186/s42400-024-00218-8