Robust Spatial-Spread Deep Neural Image Watermarking

Watermarking is an operation of embedding information into an image in a way that allows to identify ownership of the image despite applying some distortions on it. In this paper, we present a novel end-to-end solution for embedding and recovering the watermark in the digital image using convolutional neural networks. We propose a spreading method of the message over the spatial domain of the image, hence reducing the local bits per pixel capacity and significantly increasing robustness. To obtain the model we use adversarial training, apply noiser layers between the encoder and the decoder, and implement a precise JPEG approximation. Moreover, we broaden the spectrum of typically considered attacks on the watermark and we achieve high overall robustness, most notably against JPEG compression, Gaussian blur, subsampling or resizing. We show that an application of some attacks could increase robustness against other non-seen during training distortions across one group of attacks - a proper grouping of the attacks according to their scope allows to achieve high general robustness.