ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks

This work has been submitted to the IEEE for possible publication. Abstract--Due to the rapid growth of machine learning tools and specifically deep networks in various computer vision and image processing areas, applications of Convolutional Neural Networks for watermarking have recently emerged. In this paper, we propose a deep end-to-end diffusion watermarking framework (ReDMark) which can be adapted for any desired transform space. The framework is composed of two Fully Convolutional Neural Networks with the residual structure for embedding and extraction. The whole deep network is trained end-to-end to conduct a blind secure watermarking. The framework is customizable for the level of robustness vs. imperceptibility. It is also adjustable for the tradeoff between capacity and robustness. The proposed framework simulates various attacks as a differentiable network layer to facilitate end-to-end training. For JPEG attack, a differentiable approximation is utilized, which drastically improves the watermarking robustness to this attack. Another important characteristic of the proposed framework, which leads to improved security and robustness, is its capability to diffuse watermark data among a relatively wide area of the image. Comparative results versus recent state-of-the-art researches highlight the superiority of the proposed framework in terms of imperceptibility and robustness. IGITAL watermarking was originally introduced in 1979 for anti-counterfeit purposes [1] to distinguish between the original and counterfeit documents. Since then it has been applied for identification of image ownership and protection of intellectual property by hiding data such as logos and proprietary information in images, videos and audios [2]. Another application is the patient identification and medical procedure matching by hiding patients' personal information Mahdi Ahmadi, Alireza Norouzi and Nader Karimi (Member, IEEE) are with the Department of Electrical and Computer Engineering, Isfahan University of Technology, 84156-83111, Iran. S.M.Reza Soroushmehr (Member, IEEE) is with the Dept. of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, 48109 U.S.A (Email: ssoroush@med.umich.edu)