{"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/fixed-neural-network-steganography-train-the","title":"Fixed Neural Network Steganography: Train the images, not the network","arxiv_id":null,"date":"2021-09-29","proceeding":"ICLR 2022 4","authors":["Varsha Kishore","Xiangyu Chen","Yan Wang","Boyi Li","Kilian Q Weinberger"],"abstract":"Recent attempts at image steganography make use of advances in deep learning to train an encoder-decoder network pair to hide and retrieve secret messages in images. These methods are able to hide large amounts of data, but also incur high decoding error rates (around 20\\%). In this paper, we propose a novel algorithm for steganography that takes advantage of the fact that neural networks are sensitive to tiny perturbations. Our method, Fixed Neural Network Steganography (FNNS),  achieves 0\\% error reliably for hiding up to 3 bits per pixel (bpp) of secret information in images and yields significantly lower error rates when compared to prior state of the art methods for hiding more than 3 bpp. FNNS also successfully evades existing statistical steganalysis systems and can be modified to evade neural steganalysis systems as well. Recovering every bit correctly, up to 3 bpp, enables novel applications, e.g. those requiring encryption.\nWe introduce one specific use case for facilitating anonymized and safe image sharing. \n","url_abs":"https://openreview.net/forum?id=hcMvApxGSzZ","url_pdf":"https://openreview.net/pdf?id=hcMvApxGSzZ","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":"fixed-neural-network-steganography-train-the","repo_url":"https://github.com/varshakishore/FNNS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-steganography","task_name":"Image Steganography"},{"task_slug":"steganalysis","task_name":"Steganalysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}