{"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/cryptonn-training-neural-networks-over","title":"CryptoNN: Training Neural Networks over Encrypted Data","arxiv_id":"1904.07303","date":"2019-04-15","proceeding":null,"authors":["Runhua Xu","James B. D. Joshi","Chao Li"],"abstract":"Emerging neural networks based machine learning techniques such as deep\nlearning and its variants have shown tremendous potential in many application\ndomains. However, they raise serious privacy concerns due to the risk of\nleakage of highly privacy-sensitive data when data collected from users is used\nto train neural network models to support predictive tasks. To tackle such\nserious privacy concerns, several privacy-preserving approaches have been\nproposed in the literature that use either secure multi-party computation (SMC)\nor homomorphic encryption (HE) as the underlying mechanisms. However, neither\nof these cryptographic approaches provides an efficient solution towards\nconstructing a privacy-preserving machine learning model, as well as supporting\nboth the training and inference phases. To tackle the above issue, we propose a\nCryptoNN framework that supports training a neural network model over encrypted\ndata by using the emerging functional encryption scheme instead of SMC or HE.\nWe also construct a functional encryption scheme for basic arithmetic\ncomputation to support the requirement of the proposed CryptoNN framework. We\npresent performance evaluation and security analysis of the underlying crypto\nscheme and show through our experiments that CryptoNN achieves accuracy that is\nsimilar to those of the baseline neural network models on the MNIST dataset.","url_abs":"http://arxiv.org/abs/1904.07303v2","url_pdf":"http://arxiv.org/pdf/1904.07303v2.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":"cryptonn-training-neural-networks-over","repo_url":"https://github.com/iRxyzzz/nn-emd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}