Robust Spatial-spread Deep Neural Image Watermarking
This work addresses the need for robust ownership identification in digital images, though it appears incremental as it builds on existing neural network approaches with specific enhancements.
The paper tackles the problem of robust digital image watermarking by introducing an end-to-end convolutional neural network method that spreads the message spatially to reduce local capacity, achieving high general robustness against a broad spectrum of attacks including JPEG compression, Gaussian blurring, subsampling, and resizing.
Watermarking is an operation of embedding an 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 presented a novel end-to-end solution for embedding and recovering the watermark in the digital image using convolutional neural networks. The method is based on spreading the message over the spatial domain of the image, hence reducing the "local bits per pixel" capacity. To obtain the model we used adversarial training and applied noiser layers between the encoder and the decoder. Moreover, we broadened the spectrum of typically considered attacks on the watermark and by grouping the attacks according to their scope, we achieved high general robustness, most notably against JPEG compression, Gaussian blurring, subsampling or resizing. To help us in the models training we also proposed a precise differentiable approximation of JPEG.