{"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/privacy-preserving-deep-inference-for-rich","title":"Privacy-Preserving Deep Inference for Rich User Data on The Cloud","arxiv_id":"1710.01727","date":"2017-10-04","proceeding":null,"authors":["Seyed Ali Osia","Ali Shahin Shamsabadi","Ali Taheri","Kleomenis Katevas","Hamid R. Rabiee","Nicholas D. Lane","Hamed Haddadi"],"abstract":"Deep neural networks are increasingly being used in a variety of machine\nlearning applications applied to rich user data on the cloud. However, this\napproach introduces a number of privacy and efficiency challenges, as the cloud\noperator can perform secondary inferences on the available data. Recently,\nadvances in edge processing have paved the way for more efficient, and private,\ndata processing at the source for simple tasks and lighter models, though they\nremain a challenge for larger, and more complicated models. In this paper, we\npresent a hybrid approach for breaking down large, complex deep models for\ncooperative, privacy-preserving analytics. We do this by breaking down the\npopular deep architectures and fine-tune them in a particular way. We then\nevaluate the privacy benefits of this approach based on the information exposed\nto the cloud service. We also asses the local inference cost of different\nlayers on a modern handset for mobile applications. Our evaluations show that\nby using certain kind of fine-tuning and embedding techniques and at a small\nprocessing costs, we can greatly reduce the level of information available to\nunintended tasks applied to the data feature on the cloud, and hence achieving\nthe desired tradeoff between privacy and performance.","url_abs":"http://arxiv.org/abs/1710.01727v3","url_pdf":"http://arxiv.org/pdf/1710.01727v3.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":"privacy-preserving-deep-inference-for-rich","repo_url":"https://github.com/aliosia/DeepPrivInf2017","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}