A novel noiselayer-decoder driven blind watermarking network

Most blind watermarking methods adopt the Encode-Noiselayer-Decoder network architecture, called END. However, there are issues that impact the imperceptibility and robustness of the watermarking, such as the encoder blindly embedding redundant features, adversarial training failing to simulate unknown noise effectively, and the limited capability of single-scale feature extraction. To address these challenges, we propose a new Noiselayer-Decoder-driven blind watermarking network, called ND-END, which leverages prior knowledge of the noise layer and features extracted by the decoder to guide the encoder for generating images with fewer redundant modifications, enhancing the imperceptibility. To effectively simulate the unknown noise caused during adversarial training, we introduce an unknown noise layer based on the guided denoising diffusion probabilistic model, which gradually modifies the mean value of the predicted noise during the image generation process. It produces unknown noise images that closely resemble the encoded images but can mislead the decoder. Moreover, we propose a multi-scale spatial-channel feature extraction method for extracting multi-scale message features from the noised image, which aids in message extraction. Experimental results demonstrate the effectiveness of our model, ND-END achieves a lower bit error rate while improving the peak signal-to-noise ratio by approximately 6 dB (from about 33.5 dB to 39.5 dB).