Saved in:
Bibliographic Details
Main Authors: Ishida, Shoma, Ono, Satoshi
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2012.11138
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914860081610752
author Ishida, Shoma
Ono, Satoshi
author_facet Ishida, Shoma
Ono, Satoshi
contents This paper proposes a black-box adversarial attack method to automatic speech recognition systems. Some studies have attempted to attack neural networks for speech recognition; however, these methods did not consider the robustness of generated adversarial examples against timing lag with a target speech. The proposed method in this paper adopts Evolutionary Multi-objective Optimization (EMO)that allows it generating robust adversarial examples under black-box scenario. Experimental results showed that the proposed method successfully generated adjust-free adversarial examples, which are sufficiently robust against timing lag so that an attacker does not need to take the timing of playing it against the target speech.
format Preprint
id arxiv_https___arxiv_org_abs_2012_11138
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Adjust-free adversarial example generation in speech recognition using evolutionary multi-objective optimization under black-box condition
Ishida, Shoma
Ono, Satoshi
Sound
Computation and Language
Audio and Speech Processing
This paper proposes a black-box adversarial attack method to automatic speech recognition systems. Some studies have attempted to attack neural networks for speech recognition; however, these methods did not consider the robustness of generated adversarial examples against timing lag with a target speech. The proposed method in this paper adopts Evolutionary Multi-objective Optimization (EMO)that allows it generating robust adversarial examples under black-box scenario. Experimental results showed that the proposed method successfully generated adjust-free adversarial examples, which are sufficiently robust against timing lag so that an attacker does not need to take the timing of playing it against the target speech.
title Adjust-free adversarial example generation in speech recognition using evolutionary multi-objective optimization under black-box condition
topic Sound
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2012.11138