Selective Masking Adversarial Attack on Automatic Speech Recognition Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913780078739456 |
|---|---|
| author | Fang, Zheng Zhang, Shenyi Wang, Tao Li, Bowen Zhao, Lingchen Wang, Zhangyi |
| author_facet | Fang, Zheng Zhang, Shenyi Wang, Tao Li, Bowen Zhao, Lingchen Wang, Zhangyi |
| contents | Extensive research has shown that Automatic Speech Recognition (ASR) systems are vulnerable to audio adversarial attacks. Current attacks mainly focus on single-source scenarios, ignoring dual-source scenarios where two people are speaking simultaneously. To bridge the gap, we propose a Selective Masking Adversarial attack, namely SMA attack, which ensures that one audio source is selected for recognition while the other audio source is muted in dual-source scenarios. To better adapt to the dual-source scenario, our SMA attack constructs the normal dual-source audio from the muted audio and selected audio. SMA attack initializes the adversarial perturbation with a small Gaussian noise and iteratively optimizes it using a selective masking optimization algorithm. Extensive experiments demonstrate that the SMA attack can generate effective and imperceptible audio adversarial examples in the dual-source scenario, achieving an average success rate of attack of 100% and signal-to-noise ratio of 37.15dB on Conformer-CTC, outperforming the baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04394 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Selective Masking Adversarial Attack on Automatic Speech Recognition Systems Fang, Zheng Zhang, Shenyi Wang, Tao Li, Bowen Zhao, Lingchen Wang, Zhangyi Cryptography and Security Sound Extensive research has shown that Automatic Speech Recognition (ASR) systems are vulnerable to audio adversarial attacks. Current attacks mainly focus on single-source scenarios, ignoring dual-source scenarios where two people are speaking simultaneously. To bridge the gap, we propose a Selective Masking Adversarial attack, namely SMA attack, which ensures that one audio source is selected for recognition while the other audio source is muted in dual-source scenarios. To better adapt to the dual-source scenario, our SMA attack constructs the normal dual-source audio from the muted audio and selected audio. SMA attack initializes the adversarial perturbation with a small Gaussian noise and iteratively optimizes it using a selective masking optimization algorithm. Extensive experiments demonstrate that the SMA attack can generate effective and imperceptible audio adversarial examples in the dual-source scenario, achieving an average success rate of attack of 100% and signal-to-noise ratio of 37.15dB on Conformer-CTC, outperforming the baselines. |
| title | Selective Masking Adversarial Attack on Automatic Speech Recognition Systems |
| topic | Cryptography and Security Sound |
| url | https://arxiv.org/abs/2504.04394 |