Model Copyright Protection in Buyer-seller Environment

The approaches are very secure, however, the computational complexity of decryption is generally Deep neural networks (DNNs) show prominent superiority in not less than O(n). Even in the best case, the computational a large variety of fields, including self-driving cars [1], facial overhead increases linearly with DNN size, which recognition authorization [2], object detection [3], etc. is not suitable for buyers with limited computing resources. Training neural network models is expensive, which relies on Some researchers apply the selective encryption to reduce extensive datasets and computing resources. However, the resources the computational complexity of encryption and decryption of ordinary institutions or individuals are not always [8, 9]. In [8], the model can only be executed on trusted hardware.