Weighted-Sampling Audio Adversarial Example Attack

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Xiaolei, Zhang, Xiaosong, Wan, Kun, Zhu, Qingxin, Ding, Yufei
Format: Preprint
Published: 2019
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914709638217728
author Liu, Xiaolei
Zhang, Xiaosong
Wan, Kun
Zhu, Qingxin
Ding, Yufei
author_facet Liu, Xiaolei
Zhang, Xiaosong
Wan, Kun
Zhu, Qingxin
Ding, Yufei
contents Recent studies have highlighted audio adversarial examples as a ubiquitous threat to state-of-the-art automatic speech recognition systems. Thorough studies on how to effectively generate adversarial examples are essential to prevent potential attacks. Despite many research on this, the efficiency and the robustness of existing works are not yet satisfactory. In this paper, we propose~\textit{weighted-sampling audio adversarial examples}, focusing on the numbers and the weights of distortion to reinforce the attack. Further, we apply a denoising method in the loss function to make the adversarial attack more imperceptible. Experiments show that our method is the first in the field to generate audio adversarial examples with low noise and high audio robustness at the minute time-consuming level.
format Preprint
id arxiv_https___arxiv_org_abs_1901_10300
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Weighted-Sampling Audio Adversarial Example Attack
Liu, Xiaolei
Zhang, Xiaosong
Wan, Kun
Zhu, Qingxin
Ding, Yufei
Audio and Speech Processing
Sound
Recent studies have highlighted audio adversarial examples as a ubiquitous threat to state-of-the-art automatic speech recognition systems. Thorough studies on how to effectively generate adversarial examples are essential to prevent potential attacks. Despite many research on this, the efficiency and the robustness of existing works are not yet satisfactory. In this paper, we propose~\textit{weighted-sampling audio adversarial examples}, focusing on the numbers and the weights of distortion to reinforce the attack. Further, we apply a denoising method in the loss function to make the adversarial attack more imperceptible. Experiments show that our method is the first in the field to generate audio adversarial examples with low noise and high audio robustness at the minute time-consuming level.
title Weighted-Sampling Audio Adversarial Example Attack
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/1901.10300