Deep neural networks have achieved great success in varieties of artificial intelligent fields. Since training a good deep model is often challenging and costly, such deep models are of great value and even the key co...Deep neural networks have achieved great success in varieties of artificial intelligent fields. Since training a good deep model is often challenging and costly, such deep models are of great value and even the key commercial intellectual properties. Recently, deep model intellectual property protection has drawn great attention from both academia and industry, and numerous works have been proposed. However, most of them focus on the classification task. In this paper, we present the first attempt at protecting deep semantic segmentation models from potential infringements. In details, we design a new hybrid intellectual property protection framework by combining the trigger-set based and passport based watermarking simultaneously. Within it, the trigger-set based watermarking mechanism aims to force the network output copyright watermarks for a pre-defined trigger image set, which enables black-box remote ownership verification. And the passport based watermarking mechanism is to eliminate the ambiguity attack risk of trigger-set based watermarking by adding an extra passport layer into the target model. Through extensive experiments, the proposed framework not only demonstrates its effectiveness upon existing segmentation models, but also shows strong robustness to different attack techniques.展开更多
基金supported in part by the National Natural Science Foundation of China(Grant Nos.61872189,41975183,61825601)in part by the Natural Science Foundation of Jiangsu Province(BK20191397).
文摘Deep neural networks have achieved great success in varieties of artificial intelligent fields. Since training a good deep model is often challenging and costly, such deep models are of great value and even the key commercial intellectual properties. Recently, deep model intellectual property protection has drawn great attention from both academia and industry, and numerous works have been proposed. However, most of them focus on the classification task. In this paper, we present the first attempt at protecting deep semantic segmentation models from potential infringements. In details, we design a new hybrid intellectual property protection framework by combining the trigger-set based and passport based watermarking simultaneously. Within it, the trigger-set based watermarking mechanism aims to force the network output copyright watermarks for a pre-defined trigger image set, which enables black-box remote ownership verification. And the passport based watermarking mechanism is to eliminate the ambiguity attack risk of trigger-set based watermarking by adding an extra passport layer into the target model. Through extensive experiments, the proposed framework not only demonstrates its effectiveness upon existing segmentation models, but also shows strong robustness to different attack techniques.
