{"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/differentially-private-image-classification-1","title":"Differentially Private Image Classification by Learning Priors from Random Processes","arxiv_id":null,"date":"2023-09-21","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"In privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) performs worse than SGD due to per-sample gradient clipping and noise addition.\nA recent focus in private learning research is improving the performance of DP-SGD on private data by incorporating priors that are learned on real-world public data.\nIn this work, we explore how we can improve the privacy-utility tradeoff of DP-SGD by learning priors from images generated by random processes and transferring these priors to private data. \nWe propose DP-RandP, a three-phase approach. \nWe attain new state-of-the-art accuracy when training from scratch on CIFAR10, CIFAR100, MedMNIST and ImageNet for a range of privacy budgets $\\\\varepsilon \\\\in [1, 8]$. In particular, we improve the previous best reported accuracy on CIFAR10 from $60.6 \\\\%$ to $72.3 \\\\%$ for $\\\\varepsilon=1$.Submission Number: 4213","url_abs":"https://openreview.net/forum?id=P0Avuii9iI","url_pdf":"https://openreview.net/pdf?id=P0Avuii9iI","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":"differentially-private-image-classification-1","repo_url":"https://github.com/inspire-group/dp-randp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"gradient-clipping","method_name":"Gradient Clipping"},{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}