AD2T: Adversarial Distortion Domain Translation for Robust Watermarking against Non-differentiable Distortions

Abstract

Deep watermarking models optimize robustness by incorporating distortions between the encoder and decoder. To tackle non-differentiable distortions, current methods only train the decoder with distorted images, which breaks the joint optimization of the encoder-decoder, resulting in suboptimal performance. To address this problem, we propose an Adversarial Distortion Domain Translation (AD<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>T) method by treating the distortion as an image-to-image translation task. AD<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>T adopts conditional GANs to learn the non-differentiable distortion mappings. It employs generators to transform the encoded image into the distorted one to bridge the encoder-decoder for joint optimization. We also supervise the GANs to generate challenging distorted samples to augment the watermarking model via adversarial training. This further improves the model robustness by minimizing the maximum decoding loss. Extensive experiments demonstrate the superiority of our method when tested on non-differentiable distortions, including lossy compression and style transfers. Codes are released here: https://github.com/zcx-language/AdversarialDistortionDomainTranslation.