2025-01-14-wang25f.md

title	Diffusion-based Adversarial Attack to Automatic Speech Recognition
booktitle	Proceedings of the 16th Asian Conference on Machine Learning
year	2025
volume	260
series	Proceedings of Machine Learning Research
month	0
publisher	PMLR
pdf	https://raw.githubusercontent.com/mlresearch/v260/main/assets/wang25f/wang25f.pdf
url	https://proceedings.mlr.press/v260/wang25f.html
openreview	rmPwZmVaSp
abstract	Recent studies have exposed the substantial vulnerability of voice-activated smart devices to adversarial examples, predominantly targeting the robustness of automatic speech recognition (ASR) systems. Most of adversarial examples generated by introducing adversarial perturbations within the $l_p$ norm bounds to benign audio inputs. However, these attacks are constrained by the parametric bounds of perturbations or the features of disturbance, which limits their effectiveness. To improve the acoustic realism of adversarial examples and enhance attack performance, we propose a novel attack framework called Diffusion-based Adversarial Attack, leveraging DiffVC, a diffusion-based voice conversion model, to map audio to a latent space and employing Adversarial Latent Perturbation (ALP) to embed less perceptible and more robust perturbations. Extensive evaluations demonstrate that our method enhances targeted attack performance. Notably, the Word Error Rate (WER) has shown an average increase of 101 absolute points over clean speech audio and 25 absolute points over C&W attack. Additionally, the Success Rate (SR) has achieved an average increase of 11 absolute points over the C&W attack and 16 absolute points over SSA attack. Additionally, our approach also stands out for its high audio quality and efficiency.
layout	inproceedings
issn	2640-3498
id	wang25f
tex_title	Diffusion-based Adversarial Attack to Automatic Speech Recognition
firstpage	889
lastpage	904
page	889-904
order	889
cycles	false
bibtex_editor	Nguyen, Vu and Lin, Hsuan-Tien
editor	given family Vu Nguyen given family Hsuan-Tien Lin
bibtex_author	Wang, Ying and Luo, Yuchuan and Fu, Shaojing and Qiu, Zhenyu and Liu, Lin
author	given family Ying Wang given family Yuchuan Luo given family Shaojing Fu given family Zhenyu Qiu given family Lin Liu
date	2025-01-14
address
container-title	Proceedings of the 16th Asian Conference on Machine Learning
genre	inproceedings
issued	date-parts 2025 1 14
extras