CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909566308974592 |
|---|---|
| author | Li, Yiming Yan, Kaiying Shao, Shuo Zhai, Tongqing Xia, Shu-Tao Qin, Zhan Tao, Dacheng |
| author_facet | Li, Yiming Yan, Kaiying Shao, Shuo Zhai, Tongqing Xia, Shu-Tao Qin, Zhan Tao, Dacheng |
| contents | With the increasing adoption of deep learning in speaker verification, large-scale speech datasets have become valuable intellectual property. To audit and prevent the unauthorized usage of these valuable released datasets, especially in commercial or open-source scenarios, we propose a novel dataset ownership verification method. Our approach introduces a clustering-based backdoor watermark (CBW), enabling dataset owners to determine whether a suspicious third-party model has been trained on a protected dataset under a black-box setting. The CBW method consists of two key stages: dataset watermarking and ownership verification. During watermarking, we implant multiple trigger patterns in the dataset to make similar samples (measured by their feature similarities) close to the same trigger while dissimilar samples are near different triggers. This ensures that any model trained on the watermarked dataset exhibits specific misclassification behaviors when exposed to trigger-embedded inputs. To verify dataset ownership, we design a hypothesis-test-based framework that statistically evaluates whether a suspicious model exhibits the expected backdoor behavior. We conduct extensive experiments on benchmark datasets, verifying the effectiveness and robustness of our method against potential adaptive attacks. The code for reproducing main experiments is available at https://github.com/Radiant0726/CBW |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05794 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking Li, Yiming Yan, Kaiying Shao, Shuo Zhai, Tongqing Xia, Shu-Tao Qin, Zhan Tao, Dacheng Cryptography and Security Artificial Intelligence Machine Learning Sound Audio and Speech Processing With the increasing adoption of deep learning in speaker verification, large-scale speech datasets have become valuable intellectual property. To audit and prevent the unauthorized usage of these valuable released datasets, especially in commercial or open-source scenarios, we propose a novel dataset ownership verification method. Our approach introduces a clustering-based backdoor watermark (CBW), enabling dataset owners to determine whether a suspicious third-party model has been trained on a protected dataset under a black-box setting. The CBW method consists of two key stages: dataset watermarking and ownership verification. During watermarking, we implant multiple trigger patterns in the dataset to make similar samples (measured by their feature similarities) close to the same trigger while dissimilar samples are near different triggers. This ensures that any model trained on the watermarked dataset exhibits specific misclassification behaviors when exposed to trigger-embedded inputs. To verify dataset ownership, we design a hypothesis-test-based framework that statistically evaluates whether a suspicious model exhibits the expected backdoor behavior. We conduct extensive experiments on benchmark datasets, verifying the effectiveness and robustness of our method against potential adaptive attacks. The code for reproducing main experiments is available at https://github.com/Radiant0726/CBW |
| title | CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking |
| topic | Cryptography and Security Artificial Intelligence Machine Learning Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2503.05794 |