HiddenSpeaker: Generate Imperceptible Unlearnable Audios for Speaker Verification System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Zhisheng, Huang, Pengyang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910600758558720
author Zhang, Zhisheng
Huang, Pengyang
author_facet Zhang, Zhisheng
Huang, Pengyang
contents In recent years, the remarkable advancements in deep neural networks have brought tremendous convenience. However, the training process of a highly effective model necessitates a substantial quantity of samples, which brings huge potential threats, like unauthorized exploitation with privacy leakage. In response, we propose a framework named HiddenSpeaker, embedding imperceptible perturbations within the training speech samples and rendering them unlearnable for deep-learning-based speaker verification systems that employ large-scale speakers for efficient training. The HiddenSpeaker utilizes a simplified error-minimizing method named Single-Level Error-Minimizing (SLEM) to generate specific and effective perturbations. Additionally, a hybrid objective function is employed for human perceptual optimization, ensuring the perturbation is indistinguishable from human listeners. We conduct extensive experiments on multiple state-of-the-art (SOTA) models in the speaker verification domain to evaluate HiddenSpeaker. Our results demonstrate that HiddenSpeaker not only deceives the model with unlearnable samples but also enhances the imperceptibility of the perturbations, showcasing strong transferability across different models.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15655
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HiddenSpeaker: Generate Imperceptible Unlearnable Audios for Speaker Verification System
Zhang, Zhisheng
Huang, Pengyang
Sound
Machine Learning
Audio and Speech Processing
In recent years, the remarkable advancements in deep neural networks have brought tremendous convenience. However, the training process of a highly effective model necessitates a substantial quantity of samples, which brings huge potential threats, like unauthorized exploitation with privacy leakage. In response, we propose a framework named HiddenSpeaker, embedding imperceptible perturbations within the training speech samples and rendering them unlearnable for deep-learning-based speaker verification systems that employ large-scale speakers for efficient training. The HiddenSpeaker utilizes a simplified error-minimizing method named Single-Level Error-Minimizing (SLEM) to generate specific and effective perturbations. Additionally, a hybrid objective function is employed for human perceptual optimization, ensuring the perturbation is indistinguishable from human listeners. We conduct extensive experiments on multiple state-of-the-art (SOTA) models in the speaker verification domain to evaluate HiddenSpeaker. Our results demonstrate that HiddenSpeaker not only deceives the model with unlearnable samples but also enhances the imperceptibility of the perturbations, showcasing strong transferability across different models.
title HiddenSpeaker: Generate Imperceptible Unlearnable Audios for Speaker Verification System
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2405.15655