ENCRYPTION RESISTANT DEEP NEURAL NETWORK WATERMARKING

Deep neural network (DNN) watermarking is one of the main techniques to protect the DNN. Although various DNN watermarking schemes have been proposed, none of them is able to resist the DNN encryption. In this paper, we propose an encryption resistant DNN watermarking scheme, which is able to resist the parameter shuffling based DNN encryption. Unlike the existing schemes which use the kernels separately for watermarking embedding, we propose to embed the watermark into a fused kernel to resist the parameter shuffling. We further propose a MappingNet to map the fused kernel into a higher dimension to increase the watermarking capacity. The MappingNet and the DNN are jointly learnt for high watermarking performance. Experimental results indicate the effectiveness of our proposed scheme for resisting the DNN encryption.