MOVE: Effective and Harmless Ownership Verification via Embedded External Features
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929736624635904 |
|---|---|
| author | Li, Yiming Zhu, Linghui Jia, Xiaojun Bai, Yang Jiang, Yong Xia, Shu-Tao Cao, Xiaochun Ren, Kui |
| author_facet | Li, Yiming Zhu, Linghui Jia, Xiaojun Bai, Yang Jiang, Yong Xia, Shu-Tao Cao, Xiaochun Ren, Kui |
| contents | Currently, deep neural networks (DNNs) are widely adopted in different applications. Despite its commercial values, training a well-performing DNN is resource-consuming. Accordingly, the well-trained model is valuable intellectual property for its owner. However, recent studies revealed the threats of model stealing, where the adversaries can obtain a function-similar copy of the victim model, even when they can only query the model. In this paper, we propose an effective and harmless model ownership verification (MOVE) to defend against different types of model stealing simultaneously, without introducing new security risks. In general, we conduct the ownership verification by verifying whether a suspicious model contains the knowledge of defender-specified external features. Specifically, we embed the external features by modifying a few training samples with style transfer. We then train a meta-classifier to determine whether a model is stolen from the victim. This approach is inspired by the understanding that the stolen models should contain the knowledge of features learned by the victim model. In particular, \revision{we develop our MOVE method under both white-box and black-box settings and analyze its theoretical foundation to provide comprehensive model protection.} Extensive experiments on benchmark datasets verify the effectiveness of our method and its resistance to potential adaptive attacks. The codes for reproducing the main experiments of our method are available at https://github.com/THUYimingLi/MOVE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2208_02820 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | MOVE: Effective and Harmless Ownership Verification via Embedded External Features Li, Yiming Zhu, Linghui Jia, Xiaojun Bai, Yang Jiang, Yong Xia, Shu-Tao Cao, Xiaochun Ren, Kui Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Currently, deep neural networks (DNNs) are widely adopted in different applications. Despite its commercial values, training a well-performing DNN is resource-consuming. Accordingly, the well-trained model is valuable intellectual property for its owner. However, recent studies revealed the threats of model stealing, where the adversaries can obtain a function-similar copy of the victim model, even when they can only query the model. In this paper, we propose an effective and harmless model ownership verification (MOVE) to defend against different types of model stealing simultaneously, without introducing new security risks. In general, we conduct the ownership verification by verifying whether a suspicious model contains the knowledge of defender-specified external features. Specifically, we embed the external features by modifying a few training samples with style transfer. We then train a meta-classifier to determine whether a model is stolen from the victim. This approach is inspired by the understanding that the stolen models should contain the knowledge of features learned by the victim model. In particular, \revision{we develop our MOVE method under both white-box and black-box settings and analyze its theoretical foundation to provide comprehensive model protection.} Extensive experiments on benchmark datasets verify the effectiveness of our method and its resistance to potential adaptive attacks. The codes for reproducing the main experiments of our method are available at https://github.com/THUYimingLi/MOVE. |
| title | MOVE: Effective and Harmless Ownership Verification via Embedded External Features |
| topic | Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2208.02820 |