{"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-text-with-lstms","title":"Generating Steganographic Text with LSTMs","arxiv_id":"1705.10742","date":"2017-05-30","proceeding":"ACL 2017 7","authors":["Tina Fang","Martin Jaggi","Katerina Argyraki"],"abstract":"Motivated by concerns for user privacy, we design a steganographic system\n(\"stegosystem\") that enables two users to exchange encrypted messages without\nan adversary detecting that such an exchange is taking place. We propose a new\nlinguistic stegosystem based on a Long Short-Term Memory (LSTM) neural network.\nWe demonstrate our approach on the Twitter and Enron email datasets and show\nthat it yields high-quality steganographic text while significantly improving\ncapacity (encrypted bits per word) relative to the state-of-the-art.","url_abs":"http://arxiv.org/abs/1705.10742v1","url_pdf":"http://arxiv.org/pdf/1705.10742v1.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-text-with-lstms","repo_url":"https://github.com/harvardnlp/NeuralSteganography","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.10742","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}