Phantom in the opera: adversarial music attack for robot dialogue system
This study explores the vulnerability of robot dialogue systems' automatic speech recognition (ASR) module to adversarial music attacks. Specifically, we explore music as a natural camouflage for such attacks. We propose a novel method to hide ghost speech commands in a music clip by slightly p...
Main Authors: | Sheng Li, Jiyi Li, Yang Cao |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2024-02-01
|
Series: | Frontiers in Computer Science |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fcomp.2024.1355975/full |
Similar Items
-
Class Retrieval of Detected Adversarial Attacks
by: Jalal Al-afandi, et al.
Published: (2021-07-01) -
SGMA: a novel adversarial attack approach with improved transferability
by: Peican Zhu, et al.
Published: (2023-04-01) -
Adversarial Attack and Defense Strategies of Speaker Recognition Systems: A Survey
by: Hao Tan, et al.
Published: (2022-07-01) -
Boosting Adversarial Attacks with Nadam Optimizer
by: Qikun Zhang, et al.
Published: (2023-03-01) -
Adversarial Attack and Defense: A Survey
by: Hongshuo Liang, et al.
Published: (2022-04-01)