{"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/deep-private-feature-extraction","title":"Deep Private-Feature Extraction","arxiv_id":"1802.03151","date":"2018-02-09","proceeding":null,"authors":["Seyed Ali Osia","Ali Taheri","Ali Shahin Shamsabadi","Kleomenis Katevas","Hamed Haddadi","Hamid R. Rabiee"],"abstract":"We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model\nwhich is trained and evaluated based on information theoretic constraints.\nUsing the selective exchange of information between a user's device and a\nservice provider, DPFE enables the user to prevent certain sensitive\ninformation from being shared with a service provider, while allowing them to\nextract approved information using their model. We introduce and utilize the\nlog-rank privacy, a novel measure to assess the effectiveness of DPFE in\nremoving sensitive information and compare different models based on their\naccuracy-privacy tradeoff. We then implement and evaluate the performance of\nDPFE on smartphones to understand its complexity, resource demands, and\nefficiency tradeoffs. Our results on benchmark image datasets demonstrate that\nunder moderate resource utilization, DPFE can achieve high accuracy for primary\ntasks while preserving the privacy of sensitive features.","url_abs":"http://arxiv.org/abs/1802.03151v2","url_pdf":"http://arxiv.org/pdf/1802.03151v2.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":"deep-private-feature-extraction","repo_url":"https://github.com/aliosia/DPFE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.03151","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}