{"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/invisible-steganography-via-generative","title":"Invisible Steganography via Generative Adversarial Networks","arxiv_id":"1807.08571","date":"2018-07-23","proceeding":null,"authors":["Ru Zhang","Shiqi Dong","Jianyi Liu"],"abstract":"Nowadays, there are plenty of works introducing convolutional neural networks\n(CNNs) to the steganalysis and exceeding conventional steganalysis algorithms.\nThese works have shown the improving potential of deep learning in information\nhiding domain. There are also several works based on deep learning to do image\nsteganography, but these works still have problems in capacity, invisibility\nand security. In this paper, we propose a novel CNN architecture named as\n\\isgan to conceal a secret gray image into a color cover image on the sender\nside and exactly extract the secret image out on the receiver side. There are\nthree contributions in our work: (i) we improve the invisibility by hiding the\nsecret image only in the Y channel of the cover image; (ii) We introduce the\ngenerative adversarial networks to strengthen the security by minimizing the\ndivergence between the empirical probability distributions of stego images and\nnatural images. (iii) In order to associate with the human visual system\nbetter, we construct a mixed loss function which is more appropriate for\nsteganography to generate more realistic stego images and reveal out more\nbetter secret images. Experiment results show that ISGAN can achieve\nstart-of-art performances on LFW, Pascal VOC2012 and ImageNet datasets.","url_abs":"http://arxiv.org/abs/1807.08571v3","url_pdf":"http://arxiv.org/pdf/1807.08571v3.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":"invisible-steganography-via-generative","repo_url":"https://github.com/Neykah/isgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-steganography","task_name":"Image Steganography"},{"task_slug":"steganalysis","task_name":"Steganalysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.08571","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}