{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/redmark-framework-for-residual-diffusion","title":"ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks","arxiv_id":"1810.07248","date":"2018-10-16","proceeding":null,"authors":["Mahdi Ahmadi","Alireza Norouzi","S. M. Reza Soroushmehr","Nader Karimi","Kayvan Najarian","Shadrokh Samavi","Ali Emami"],"abstract":"Due to the rapid growth of machine learning tools and specifically deep\nnetworks in various computer vision and image processing areas, application of\nConvolutional Neural Networks for watermarking have recently emerged. In this\npaper, we propose a deep end-to-end diffusion watermarking framework (ReDMark)\nwhich can be adapted for any desired transform space. The framework is composed\nof two Fully Convolutional Neural Networks with the residual structure for\nembedding and extraction. The whole deep network is trained end-to-end to\nconduct a blind secure watermarking. The framework is customizable for the\nlevel of robustness vs. imperceptibility. It is also adjustable for the\ntrade-off between capacity and robustness. The proposed framework simulates\nvarious attacks as a differentiable network layer to facilitate end-to-end\ntraining. For JPEG attack, a differentiable approximation is utilized, which\ndrastically improves the watermarking robustness to this attack. Another\nimportant characteristic of the proposed framework, which leads to improved\nsecurity and robustness, is its capability to diffuse watermark information\namong a relatively wide area of the image. Comparative results versus recent\nstate-of-the-art researches highlight the superiority of the proposed framework\nin terms of imperceptibility and robustness.","url_abs":"http://arxiv.org/abs/1810.07248v3","url_pdf":"http://arxiv.org/pdf/1810.07248v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"redmark-framework-for-residual-diffusion","repo_url":"https://github.com/MahdiShAhmadi/ReDMark","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.07248","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}