Intellectual Property Protection for Deep Models: Pioneering Cross-Domain Fingerprinting Solutions
- 21 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 3587-3600
Abstract
The high cost of developing high-performance deep models highlights their value as intellectual property for creators. However, it is important to consider the potential risks of theft. Although various techniques have been developed to protect the intellectual property of deep models, there is still room for improvement in terms of efficiency, comprehensiveness, and generalization. Compared with the intrusiveness of watermarking methods, fingerprinting methods do not affect the training process of the source model. Consequently, this paper proposes a fingerprinting method to address the paucity of attempts in fingerprinting methods for model protection. Our method consists of two efficient algorithms for generating fingerprinting samples, where the first one possesses the advantage of efficiency, while the second one is better in terms of robustness. The first algorithm takes a comprehensive approach to modeling the fingerprint of the deep model. The generated samples are distributed within the stable region and near the decision boundary of the model, taking into account both the duality and the conviction factors. Then, a heuristic sample perturbation algorithm is introduced, which generates a fingerprint with solid stability and generalization across multiple domains. The two algorithms proposed in this paper have been shown to be capable of withstanding attacks on intellectual property removal, detection, and evasion. They also show some advantages in terms of efficiency. In addition, the proposed method is the first to apply fingerprinting techniques in a cross-domain context.Keywords
Funding Information
- National Natural Science Foundation of China (62472291)
- Natural Science Foundation of Guangdong Province (2023A1515012685, 2025A1515012154)
- Open Fund of National Engineering Laboratory for Big Data System Computing Technology (SZU-BDSC-OF2024-14)
This publication has 28 references indexed in Scilit:
- IPCert: Provably Robust Intellectual Property Protection for Machine Learning2023
- Towards Robust Model Watermark via Reducing Parametric Vulnerability2023
- Fingerprinting Deep Image Restoration Models2023
- Protecting Intellectual Property of EEG-based Model with Watermarking2023
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks2018
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Deep learning with convolutional neural networks for EEG decoding and visualizationHuman Brain Mapping, 2017
- Densely Connected Convolutional Networks2017
- Deep Residual Learning for Image Recognition2016
- The role of asymmetric frontal cortical activity in emotion-related phenomena: A review and updateBiological Psychology, 2010