Towards robust deep hiding under non-differentiable distortions for practical blind watermarking

Abstract

Data hiding is one widely used approach for proving ownership through blind watermarking. Deep learning has been widely used in data hiding and inserting an attack simulation layer (ASL) after the watermarked image has been widely recognized as the most effective approach for improving the pipeline robustness against distortions. Despite its wide usage due to simplicity, the gain of enhanced robustness is usually interpreted through the lens of augmentation while our work explores this gain from a new perspective by disentangling the forward and backward pass of such ASL. We find that the main influential component is the forward pass instead of the backward pass. This observation motivates us to use forward ASL to make the pipeline compatible with non-differentiable and/or black-box distortion, such as lossy (JPEG) compression and photoshop effects. Extensive experiments demonstrate the efficacy of our approach despite being simple.