Audio Injection Adversarial Example Attack
Abstract
We study the problem of audio adversarial example attacks with sparse perturbations. Compared with image adversarial example attacks, attacking audio is more challenging because the audio structure is more complex and the perturbation is difficult to conceal. To overcome this challenge, we propose an audio injection adversarial example attack, which provides a new sight light to increase the concealment of attack behavior. Experiments demonstrate that the proposed audio injection adversarial example attack can significantly reduce the perturbation proportion and achieve a better attack effect than traditional attack methods.
Cite
Text
Liu et al. "Audio Injection Adversarial Example Attack." ICML 2021 Workshops: AML, 2021.Markdown
[Liu et al. "Audio Injection Adversarial Example Attack." ICML 2021 Workshops: AML, 2021.](https://mlanthology.org/icmlw/2021/liu2021icmlw-audio/)BibTeX
@inproceedings{liu2021icmlw-audio,
title = {{Audio Injection Adversarial Example Attack}},
author = {Liu, Xiaolei and Chen, Xingshu and Yin, Mingyong and Wang, Yulong and Hu, Teng and Ding, Kangyi},
booktitle = {ICML 2021 Workshops: AML},
year = {2021},
url = {https://mlanthology.org/icmlw/2021/liu2021icmlw-audio/}
}