EventTrojan: Manipulating Non-Intrusive Speech Quality Assessment via Imperceptible Events
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909310973378560 |
|---|---|
| author | Ren, Ying Shen, Kailai Ye, Zhe Yan, Diqun |
| author_facet | Ren, Ying Shen, Kailai Ye, Zhe Yan, Diqun |
| contents | Non-Intrusive speech quality assessment (NISQA) has gained significant attention for predicting speech's mean opinion score (MOS) without requiring the reference speech. Researchers have gradually started to apply NISQA to various practical scenarios. However, little attention has been paid to the security of NISQA models. Backdoor attacks represent the most serious threat to deep neural networks (DNNs) due to the fact that backdoors possess a very high attack success rate once embedded. However, existing backdoor attacks assume that the attacker actively feeds samples containing triggers into the model during the inference phase. This is not adapted to the specific scenario of NISQA. And current backdoor attacks on regression tasks lack an objective metric to measure the attack performance. To address these issues, we propose a novel backdoor triggering approach (EventTrojan) that utilizes an event during the usage of the NISQA model as a trigger. Moreover, we innovatively provide an objective metric for backdoor attacks on regression tasks. Extensive experiments on four benchmark datasets demonstrate the effectiveness of the EventTrojan attack. Besides, it also has good resistance to several defense methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_01480 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | EventTrojan: Manipulating Non-Intrusive Speech Quality Assessment via Imperceptible Events Ren, Ying Shen, Kailai Ye, Zhe Yan, Diqun Sound Artificial Intelligence Audio and Speech Processing Non-Intrusive speech quality assessment (NISQA) has gained significant attention for predicting speech's mean opinion score (MOS) without requiring the reference speech. Researchers have gradually started to apply NISQA to various practical scenarios. However, little attention has been paid to the security of NISQA models. Backdoor attacks represent the most serious threat to deep neural networks (DNNs) due to the fact that backdoors possess a very high attack success rate once embedded. However, existing backdoor attacks assume that the attacker actively feeds samples containing triggers into the model during the inference phase. This is not adapted to the specific scenario of NISQA. And current backdoor attacks on regression tasks lack an objective metric to measure the attack performance. To address these issues, we propose a novel backdoor triggering approach (EventTrojan) that utilizes an event during the usage of the NISQA model as a trigger. Moreover, we innovatively provide an objective metric for backdoor attacks on regression tasks. Extensive experiments on four benchmark datasets demonstrate the effectiveness of the EventTrojan attack. Besides, it also has good resistance to several defense methods. |
| title | EventTrojan: Manipulating Non-Intrusive Speech Quality Assessment via Imperceptible Events |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2309.01480 |