Saved in:
Bibliographic Details
Main Authors: Gao, Xiaoxue, Li, Zexin, Chen, Yiming, Liu, Cong, Li, Haizhou
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.09220
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912118572318720
author Gao, Xiaoxue
Li, Zexin
Chen, Yiming
Liu, Cong
Li, Haizhou
author_facet Gao, Xiaoxue
Li, Zexin
Chen, Yiming
Liu, Cong
Li, Haizhou
contents Given the extensive research and real-world applications of automatic speech recognition (ASR), ensuring the robustness of ASR models against minor input perturbations becomes a crucial consideration for maintaining their effectiveness in real-time scenarios. Previous explorations into ASR model robustness have predominantly revolved around evaluating accuracy on white-box settings with full access to ASR models. Nevertheless, full ASR model details are often not available in real-world applications. Therefore, evaluating the robustness of black-box ASR models is essential for a comprehensive understanding of ASR model resilience. In this regard, we thoroughly study the vulnerability of practical black-box attacks in cutting-edge ASR models and propose to employ two advanced time-domain-based transferable attacks alongside our differentiable feature extractor. We also propose a speech-aware gradient optimization approach (SAGO) for ASR, which forces mistranscription with minimal impact on human imperceptibility through voice activity detection rule and a speech-aware gradient-oriented optimizer. Our comprehensive experimental results reveal performance enhancements compared to baseline approaches across five models on two databases.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09220
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transferable Adversarial Attacks against ASR
Gao, Xiaoxue
Li, Zexin
Chen, Yiming
Liu, Cong
Li, Haizhou
Audio and Speech Processing
Artificial Intelligence
Signal Processing
Given the extensive research and real-world applications of automatic speech recognition (ASR), ensuring the robustness of ASR models against minor input perturbations becomes a crucial consideration for maintaining their effectiveness in real-time scenarios. Previous explorations into ASR model robustness have predominantly revolved around evaluating accuracy on white-box settings with full access to ASR models. Nevertheless, full ASR model details are often not available in real-world applications. Therefore, evaluating the robustness of black-box ASR models is essential for a comprehensive understanding of ASR model resilience. In this regard, we thoroughly study the vulnerability of practical black-box attacks in cutting-edge ASR models and propose to employ two advanced time-domain-based transferable attacks alongside our differentiable feature extractor. We also propose a speech-aware gradient optimization approach (SAGO) for ASR, which forces mistranscription with minimal impact on human imperceptibility through voice activity detection rule and a speech-aware gradient-oriented optimizer. Our comprehensive experimental results reveal performance enhancements compared to baseline approaches across five models on two databases.
title Transferable Adversarial Attacks against ASR
topic Audio and Speech Processing
Artificial Intelligence
Signal Processing
url https://arxiv.org/abs/2411.09220