Fingerprinting Image-to-Image Generative Adversarial Networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2021
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910558072078336 |
|---|---|
| author | Li, Guanlin Xu, Guowen Qiu, Han Guo, Shangwei Wang, Run Li, Jiwei Zhang, Tianwei Lu, Rongxing |
| author_facet | Li, Guanlin Xu, Guowen Qiu, Han Guo, Shangwei Wang, Run Li, Jiwei Zhang, Tianwei Lu, Rongxing |
| contents | Generative Adversarial Networks (GANs) have been widely used in various application scenarios. Since the production of a commercial GAN requires substantial computational and human resources, the copyright protection of GANs is urgently needed. This paper presents a novel fingerprinting scheme for the Intellectual Property (IP) protection of image-to-image GANs based on a trusted third party. We break through the stealthiness and robustness bottlenecks suffered by previous fingerprinting methods for classification models being naively transferred to GANs. Specifically, we innovatively construct a composite deep learning model from the target GAN and a classifier. Then we generate fingerprint samples from this composite model, and embed them in the classifier for effective ownership verification. This scheme inspires some concrete methodologies to practically protect the modern image-to-image translation GANs. Theoretical analysis proves that these methods can satisfy different security requirements necessary for IP protection. We also conduct extensive experiments to show that our solutions outperform existing strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2106_11760 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Fingerprinting Image-to-Image Generative Adversarial Networks Li, Guanlin Xu, Guowen Qiu, Han Guo, Shangwei Wang, Run Li, Jiwei Zhang, Tianwei Lu, Rongxing Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Generative Adversarial Networks (GANs) have been widely used in various application scenarios. Since the production of a commercial GAN requires substantial computational and human resources, the copyright protection of GANs is urgently needed. This paper presents a novel fingerprinting scheme for the Intellectual Property (IP) protection of image-to-image GANs based on a trusted third party. We break through the stealthiness and robustness bottlenecks suffered by previous fingerprinting methods for classification models being naively transferred to GANs. Specifically, we innovatively construct a composite deep learning model from the target GAN and a classifier. Then we generate fingerprint samples from this composite model, and embed them in the classifier for effective ownership verification. This scheme inspires some concrete methodologies to practically protect the modern image-to-image translation GANs. Theoretical analysis proves that these methods can satisfy different security requirements necessary for IP protection. We also conduct extensive experiments to show that our solutions outperform existing strategies. |
| title | Fingerprinting Image-to-Image Generative Adversarial Networks |
| topic | Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2106.11760 |