Distortion Agnostic Deep Watermarking
This addresses a key limitation in watermarking for image security, enabling robustness to unpredictable distortions, though it is incremental as it builds on existing deep learning approaches.
The paper tackles the problem of deep watermarking methods requiring differentiable distortion models at training time, which limits generalization to unknown distortions; it proposes a distortion-agnostic framework using adversarial training and channel coding, achieving comparable or better results on known distortions and improved performance on unknown ones.
Watermarking is the process of embedding information into an image that can survive under distortions, while requiring the encoded image to have little or no perceptual difference from the original image. Recently, deep learning-based methods achieved impressive results in both visual quality and message payload under a wide variety of image distortions. However, these methods all require differentiable models for the image distortions at training time, and may generalize poorly to unknown distortions. This is undesirable since the types of distortions applied to watermarked images are usually unknown and non-differentiable. In this paper, we propose a new framework for distortion-agnostic watermarking, where the image distortion is not explicitly modeled during training. Instead, the robustness of our system comes from two sources: adversarial training and channel coding. Compared to training on a fixed set of distortions and noise levels, our method achieves comparable or better results on distortions available during training, and better performance on unknown distortions.