Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection
About
As scientific and technological advancements result from human intellectual labor and computational costs, protecting model intellectual property (IP) has become increasingly important to encourage model creators and owners. Model IP protection involves preventing the use of well-trained models on unauthorized domains. To address this issue, we propose a novel approach called Compact Un-Transferable Isolation Domain (CUTI-domain), which acts as a barrier to block illegal transfers from authorized to unauthorized domains. Specifically, CUTI-domain blocks cross-domain transfers by highlighting the private style features of the authorized domain, leading to recognition failure on unauthorized domains with irrelevant private style features. Moreover, we provide two solutions for using CUTI-domain depending on whether the unauthorized domain is known or not: target-specified CUTI-domain and target-free CUTI-domain. Our comprehensive experimental results on four digit datasets, CIFAR10 & STL10, and VisDA-2017 dataset demonstrate that CUTI-domain can be easily implemented as a plug-and-play module with different backbones, providing an efficient solution for model IP protection.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Classification | SVHN (test) | Accuracy90.9 | 362 | |
| Domain Verification | Office Home 65 | Dua0.6287 | 25 | |
| Image Classification | USPS (test) | Accuracy99.6 | 25 | |
| Domain Verification | DomainNet Mini | Dua48.18 | 25 | |
| Domain Verification | Office-31 | Dua27.95 | 20 | |
| Digit Classification | USPS | Accuracy99.7 | 18 | |
| Model Intellectual Property Protection | Digit Datasets (MNIST, USPS, SVHN, MNIST-M) standard | Source Drop-0.1 | 15 | |
| Image Classification | Digits (MNIST, USPS, SVHN, MNIST-M) standard (test) | Source Drop78.4 | 15 | |
| Ownership Verification | MNIST MT | Accuracy (Watermark Patch)16.8 | 14 | |
| Digit Classification | Digit Datasets MT, US, SN, MM | Source Drop0.3 | 10 |