{"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/generating-steganographic-images-via","title":"Generating Steganographic Images via Adversarial Training","arxiv_id":"1703.00371","date":"2017-03-01","proceeding":"NeurIPS 2017 12","authors":["Jamie Hayes","George Danezis"],"abstract":"Adversarial training was recently shown to be competitive against supervised\nlearning methods on computer vision tasks, however, studies have mainly been\nconfined to generative tasks such as image synthesis. In this paper, we apply\nadversarial training techniques to the discriminative task of learning a\nsteganographic algorithm. Steganography is a collection of techniques for\nconcealing information by embedding it within a non-secret medium, such as\ncover texts or images. We show that adversarial training can produce robust\nsteganographic techniques: our unsupervised training scheme produces a\nsteganographic algorithm that competes with state-of-the-art steganographic\ntechniques, and produces a robust steganalyzer, which performs the\ndiscriminative task of deciding if an image contains secret information. We\ndefine a game between three parties, Alice, Bob and Eve, in order to\nsimultaneously train both a steganographic algorithm and a steganalyzer. Alice\nand Bob attempt to communicate a secret message contained within an image,\nwhile Eve eavesdrops on their conversation and attempts to determine if secret\ninformation is embedded within the image. We represent Alice, Bob and Eve by\nneural networks, and validate our scheme on two independent image datasets,\nshowing our novel method of studying steganographic problems is surprisingly\ncompetitive against established steganographic techniques.","url_abs":"http://arxiv.org/abs/1703.00371v3","url_pdf":"http://arxiv.org/pdf/1703.00371v3.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":"generating-steganographic-images-via","repo_url":"https://github.com/jhayes14/advsteg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.00371","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}