{"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/yedrouj-net-an-efficient-cnn-for-spatial","title":"Yedrouj-Net: An efficient CNN for spatial steganalysis","arxiv_id":"1803.00407","date":"2018-02-26","proceeding":null,"authors":["Mehdi Yedroudj","Frederic Comby","Marc Chaumont"],"abstract":"For about 10 years, detecting the presence of a secret message hidden in an\nimage was performed with an Ensemble Classifier trained with Rich features. In\nrecent years, studies such as Xu et al. have indicated that well-designed\nconvolutional Neural Networks (CNN) can achieve comparable performance to the\ntwo-step machine learning approaches.\n  In this paper, we propose a CNN that outperforms the state-ofthe-art in terms\nof error probability. The proposition is in the continuity of what has been\nrecently proposed and it is a clever fusion of important bricks used in various\npapers. Among the essential parts of the CNN, one can cite the use of a\npre-processing filterbank and a Truncation activation function, five\nconvolutional layers with a Batch Normalization associated with a Scale Layer,\nas well as the use of a sufficiently sized fully connected section. An\naugmented database has also been used to improve the training of the CNN.\n  Our CNN was experimentally evaluated against S-UNIWARD and WOW embedding\nalgorithms and its performances were compared with those of three other\nmethods: an Ensemble Classifier plus a Rich Model, and two other CNN\nsteganalyzers.","url_abs":"http://arxiv.org/abs/1803.00407v1","url_pdf":"http://arxiv.org/pdf/1803.00407v1.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":"yedrouj-net-an-efficient-cnn-for-spatial","repo_url":"https://github.com/yedmed/steganalysis_with_CNN_Yedroudj-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"steganalysis","task_name":"Steganalysis"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}