{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00228686","sets":["6164:6165:6462:11379"]},"path":["11379"],"owner":"44499","recid":"228686","title":["データコラボレーションへの差分プライバシーの適用に向けて"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-10-23"},"_buckets":{"deposit":"c56bb666-88e6-44fa-adab-5e23923e25f3"},"_deposit":{"id":"228686","pid":{"type":"depid","value":"228686","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"データコラボレーションへの差分プライバシーの適用に向けて","author_link":["613230","613233","613234","613235","613236","613232","613231","613229"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"データコラボレーションへの差分プライバシーの適用に向けて"},{"subitem_title":"Toward the Application of Differential Privacy to Data Collaboration","subitem_title_language":"en"}]},"item_type_id":"18","publish_date":"2023-10-23","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"筑波大学"},{"subitem_text_value":"筑波大学"},{"subitem_text_value":"筑波大学"},{"subitem_text_value":"筑波大学"}]},"item_18_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"University of Tsukuba","subitem_text_language":"en"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/228686/files/IPSJ-CSS2023073.pdf","label":"IPSJ-CSS2023073.pdf"},"date":[{"dateType":"Available","dateValue":"2025-10-23"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CSS2023073.pdf","filesize":[{"value":"492.2 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"30"},{"tax":["include_tax"],"price":"0","billingrole":"46"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"5122f008-4843-4412-b86b-e72e3727cbf7","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"山城, 大海"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"面, 和成"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"今倉, 暁"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"櫻井, 鉄也"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hiromi, Yamashiro","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kazumasa, Omote","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Akira, Imakura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tetsuya, Sakurai","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"分散データに対するデータ解析技術として，モデル共有型の方法であるFederated Learningと非モデル共有型の手法であるデータコラボレーションが知られている．Federated Learningは機械学習モデルのパラメタだけを，データコラボレーションは次元削減で不可逆的に加工されたデータだけを中央サーバに送信する．どちらもプライバシーに配慮して設計された方法だが，必ずしも安全ではない．Federated Learningに対しては，理論的・定量的なプライバシー基準である差分プライバシー（DP）を適用して厳密にプライバシーを保護する方法が提案されている．本論文では，データコラボレーションへのDPの適用を目指し，次元削減手法としてPCAを用いる新たな方式を提案する．提案方式を用いた実験評価では，DPなデータコラボレーションの有用性は，DPなFederated Learningと同程度であることを確認した．","subitem_description_type":"Other"}]},"item_18_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Federated Learning, a model-sharing method, and data collaboration, a non-model-sharing method, are recognized as data analysis methods for distributed data. In Federated Learning, clients send only the parameters of a machine learning model to the central server. In Data Collaboration, clients send data that has undergone irreversibly transformed through dimensionality reduction to the central server. Both methods are designed with privacy concerns, but privacy is not guaranteed. Differential Privacy, a theoretical and quantitative privacy criterion, has been applied to Federated Learning to achieve rigorous privacy preservation. In this paper, we introduce a novel method using PCA as a dimensionality reduction method, aiming to apply Differential Privacy to Data Collaboration. Experimental evaluation using the proposed method show that differentially-private Data Collaboration achieves comparable performance to differentially-private Federated Learning.","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"538","bibliographic_titles":[{"bibliographic_title":"コンピュータセキュリティシンポジウム2023論文集"}],"bibliographicPageStart":"531","bibliographicIssueDates":{"bibliographicIssueDate":"2023-10-23","bibliographicIssueDateType":"Issued"}}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:27:49.651797+00:00","updated":"2025-01-19T11:45:45.360967+00:00","id":228686}