Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929716648214528 |
|---|---|
| author | Fei, Zekun Yi, Biao Geng, Jianing He, Ruiqi Nie, Lihai Liu, Zheli |
| author_facet | Fei, Zekun Yi, Biao Geng, Jianing He, Ruiqi Nie, Lihai Liu, Zheli |
| contents | Embedding-as-a-Service (EaaS) has emerged as a successful business pattern but faces significant challenges related to various forms of copyright infringement, particularly, the API misuse and model extraction attacks. Various studies have proposed backdoor-based watermarking schemes to protect the copyright of EaaS services. In this paper, we reveal that previous watermarking schemes possess semantic-independent characteristics and propose the Semantic Perturbation Attack (SPA). Our theoretical and experimental analysis demonstrate that this semantic-independent nature makes current watermarking schemes vulnerable to adaptive attacks that exploit semantic perturbations tests to bypass watermark verification. Extensive experimental results across multiple datasets demonstrate that the True Positive Rate (TPR) for identifying watermarked samples under SPA can reach up to more than 95\%, rendering watermarks ineffective while maintaining the high utility of embeddings. Furthermore, we discuss potential defense strategies to mitigate SPA. Our code is available at https://github.com/Zk4-ps/EaaS-Embedding-Watermark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_09359 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark Fei, Zekun Yi, Biao Geng, Jianing He, Ruiqi Nie, Lihai Liu, Zheli Cryptography and Security Artificial Intelligence Embedding-as-a-Service (EaaS) has emerged as a successful business pattern but faces significant challenges related to various forms of copyright infringement, particularly, the API misuse and model extraction attacks. Various studies have proposed backdoor-based watermarking schemes to protect the copyright of EaaS services. In this paper, we reveal that previous watermarking schemes possess semantic-independent characteristics and propose the Semantic Perturbation Attack (SPA). Our theoretical and experimental analysis demonstrate that this semantic-independent nature makes current watermarking schemes vulnerable to adaptive attacks that exploit semantic perturbations tests to bypass watermark verification. Extensive experimental results across multiple datasets demonstrate that the True Positive Rate (TPR) for identifying watermarked samples under SPA can reach up to more than 95\%, rendering watermarks ineffective while maintaining the high utility of embeddings. Furthermore, we discuss potential defense strategies to mitigate SPA. Our code is available at https://github.com/Zk4-ps/EaaS-Embedding-Watermark. |
| title | Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2411.09359 |