Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909525239398400 |
|---|---|
| author | Liu, Chang Wu, Haolin Yang, Xi Zhang, Kui Wu, Cong Zhang, Weiming Yu, Nenghai Zhang, Tianwei Guo, Qing Zhang, Jie |
| author_facet | Liu, Chang Wu, Haolin Yang, Xi Zhang, Kui Wu, Cong Zhang, Weiming Yu, Nenghai Zhang, Tianwei Guo, Qing Zhang, Jie |
| contents | As speech translation (ST) systems become increasingly prevalent, understanding their vulnerabilities is crucial for ensuring robust and reliable communication. However, limited work has explored this issue in depth. This paper explores methods of compromising these systems through imperceptible audio manipulations. Specifically, we present two innovative approaches: (1) the injection of perturbation into source audio, and (2) the generation of adversarial music designed to guide targeted translation, while also conducting more practical over-the-air attacks in the physical world. Our experiments reveal that carefully crafted audio perturbations can mislead translation models to produce targeted, harmful outputs, while adversarial music achieve this goal more covertly, exploiting the natural imperceptibility of music. These attacks prove effective across multiple languages and translation models, highlighting a systemic vulnerability in current ST architectures. The implications of this research extend beyond immediate security concerns, shedding light on the interpretability and robustness of neural speech processing systems. Our findings underscore the need for advanced defense mechanisms and more resilient architectures in the realm of audio systems. More details and samples can be found at https://adv-st.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00957 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks Liu, Chang Wu, Haolin Yang, Xi Zhang, Kui Wu, Cong Zhang, Weiming Yu, Nenghai Zhang, Tianwei Guo, Qing Zhang, Jie Sound Artificial Intelligence Cryptography and Security Audio and Speech Processing As speech translation (ST) systems become increasingly prevalent, understanding their vulnerabilities is crucial for ensuring robust and reliable communication. However, limited work has explored this issue in depth. This paper explores methods of compromising these systems through imperceptible audio manipulations. Specifically, we present two innovative approaches: (1) the injection of perturbation into source audio, and (2) the generation of adversarial music designed to guide targeted translation, while also conducting more practical over-the-air attacks in the physical world. Our experiments reveal that carefully crafted audio perturbations can mislead translation models to produce targeted, harmful outputs, while adversarial music achieve this goal more covertly, exploiting the natural imperceptibility of music. These attacks prove effective across multiple languages and translation models, highlighting a systemic vulnerability in current ST architectures. The implications of this research extend beyond immediate security concerns, shedding light on the interpretability and robustness of neural speech processing systems. Our findings underscore the need for advanced defense mechanisms and more resilient architectures in the realm of audio systems. More details and samples can be found at https://adv-st.github.io. |
| title | Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks |
| topic | Sound Artificial Intelligence Cryptography and Security Audio and Speech Processing |
| url | https://arxiv.org/abs/2503.00957 |