{"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/learning-to-protect-communications-with","title":"Learning to Protect Communications with Adversarial Neural Cryptography","arxiv_id":"1610.06918","date":"2016-10-21","proceeding":null,"authors":["Martín Abadi","David G. Andersen"],"abstract":"We ask whether neural networks can learn to use secret keys to protect\ninformation from other neural networks. Specifically, we focus on ensuring\nconfidentiality properties in a multiagent system, and we specify those\nproperties in terms of an adversary. Thus, a system may consist of neural\nnetworks named Alice and Bob, and we aim to limit what a third neural network\nnamed Eve learns from eavesdropping on the communication between Alice and Bob.\nWe do not prescribe specific cryptographic algorithms to these neural networks;\ninstead, we train end-to-end, adversarially. We demonstrate that the neural\nnetworks can learn how to perform forms of encryption and decryption, and also\nhow to apply these operations selectively in order to meet confidentiality\ngoals.","url_abs":"http://arxiv.org/abs/1610.06918v1","url_pdf":"http://arxiv.org/pdf/1610.06918v1.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":"learning-to-protect-communications-with","repo_url":"https://github.com/Agwave/Pytorch-Adversarial-Neural-Cryptography","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-to-protect-communications-with","repo_url":"https://github.com/EXYNOS-999/MIT_utrc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"learning-to-protect-communications-with","repo_url":"https://github.com/IBM/MAX-Adversarial-Cryptography","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-to-protect-communications-with","repo_url":"https://github.com/Rutts07/Adversarial-Neural-Crytography","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-to-protect-communications-with","repo_url":"https://github.com/asya-b/adversarial-cnn-cryptography","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-to-protect-communications-with","repo_url":"https://github.com/avani17101/Adversarial-Neural-Crypto","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"learning-to-protect-communications-with","repo_url":"https://github.com/marcellodebernardi/adversarial-csprng","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-to-protect-communications-with","repo_url":"https://github.com/mguarin0/LearningToProtectCommunicationsWithAdversarialNeuralCryptography","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-to-protect-communications-with","repo_url":"https://github.com/tensorflow/models/tree/master/research/adversarial_crypto","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.06918","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}