摘要
Despite the tremendous success, deep neural networks are exposed to serious IP infringement risks. Given a target deep model, if the attacker knows its full information, it can be easily stolen by fine-tuning. Even if only its output is accessible, a surrogate model can be trained through student-teacher learning by generating many input-output training pairs. Therefore, deep model IP protection is important and necessary. However, it is still seriously under-researched. In this work, we propose a new model watermarking framework for protecting deep networks trained for low-level computer vision or image processing tasks. Specifically, a special task-agnostic barrier is added after the target model, which embeds a unified and invisible watermark into its outputs. When the attacker trains one surrogate model by using the input-output pairs of the barrier target model, the hidden watermark will be learned and extracted afterwards. To enable watermarks from binary bits to high-resolution images, a deep invisible watermarking mechanism is designed. By jointly training the target model and watermark embedding, the extra barrier can even be absorbed into the target model. Through extensive experiments, we demonstrate the robustness of the proposed framework, which can resist attacks with different network structures and objective functions.
学科与关键词
- Watermarking Deep Neural Networks in Image ProcessingQuan, Yuhui; Teng, Huan; Chen, Yixin; Ji, Hui*IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(5): 1852-1865.被引 23
- Intellectual property protection of DNN modelsPeng, Sen; Chen, Yufei; Xu, Jie; Chen, Zizhuo; Wang, Cong; Jia, Xiaohua*WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2023, 26(4): 1877-1911.被引 1
- Watermark Removal Scheme Based on Neural Network Model PruningGu, Wenwen*; Qian, Haifeng5th International Conference on Machine Learning and Natural Language Processing (MLNLP), Sanya, PEOPLES R CHINA, 2022-12-23 To 2022-12-25.
