Diffusion-Based Adversarial Purification for Speaker Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bai, Yibo, Zhang, Xiao-Lei, Li, Xuelong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913422299365376
author Bai, Yibo
Zhang, Xiao-Lei
Li, Xuelong
author_facet Bai, Yibo
Zhang, Xiao-Lei
Li, Xuelong
contents Recently, automatic speaker verification (ASV) based on deep learning is easily contaminated by adversarial attacks, which is a new type of attack that injects imperceptible perturbations to audio signals so as to make ASV produce wrong decisions. This poses a significant threat to the security and reliability of ASV systems. To address this issue, we propose a Diffusion-Based Adversarial Purification (DAP) method that enhances the robustness of ASV systems against such adversarial attacks. Our method leverages a conditional denoising diffusion probabilistic model to effectively purify the adversarial examples and mitigate the impact of perturbations. DAP first introduces controlled noise into adversarial examples, and then performs a reverse denoising process to reconstruct clean audio. Experimental results demonstrate the efficacy of the proposed DAP in enhancing the security of ASV and meanwhile minimizing the distortion of the purified audio signals.
format Preprint
id arxiv_https___arxiv_org_abs_2310_14270
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Diffusion-Based Adversarial Purification for Speaker Verification
Bai, Yibo
Zhang, Xiao-Lei
Li, Xuelong
Audio and Speech Processing
Sound
Recently, automatic speaker verification (ASV) based on deep learning is easily contaminated by adversarial attacks, which is a new type of attack that injects imperceptible perturbations to audio signals so as to make ASV produce wrong decisions. This poses a significant threat to the security and reliability of ASV systems. To address this issue, we propose a Diffusion-Based Adversarial Purification (DAP) method that enhances the robustness of ASV systems against such adversarial attacks. Our method leverages a conditional denoising diffusion probabilistic model to effectively purify the adversarial examples and mitigate the impact of perturbations. DAP first introduces controlled noise into adversarial examples, and then performs a reverse denoising process to reconstruct clean audio. Experimental results demonstrate the efficacy of the proposed DAP in enhancing the security of ASV and meanwhile minimizing the distortion of the purified audio signals.
title Diffusion-Based Adversarial Purification for Speaker Verification
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2310.14270