{"id":231677,"updated":"2025-01-19T10:40:11.431573+00:00","links":{},"created":"2025-01-19T01:32:07.306594+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00231677","sets":["1164:11259:11454:11455"]},"path":["11455"],"owner":"44499","recid":"231677","title":["リッチデバイス-エッジサーバ間での分散機械学習におけるプライバシ保護の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-01-15"},"_buckets":{"deposit":"c312d323-7991-4b54-a6cd-8f2208aed497"},"_deposit":{"id":"231677","pid":{"type":"depid","value":"231677","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"リッチデバイス-エッジサーバ間での分散機械学習におけるプライバシ保護の検討","author_link":["625846","625844","625843","625845"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"リッチデバイス-エッジサーバ間での分散機械学習におけるプライバシ保護の検討"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"デバイスとデータ利用","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-01-15","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"お茶の水女子大学"},{"subitem_text_value":"東京大学"},{"subitem_text_value":"工学院大学"},{"subitem_text_value":"お茶の水女子大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Ochanomizu University","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Kogakuin University","subitem_text_language":"en"},{"subitem_text_value":"Ochanomizu University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/231677/files/IPSJ-CN24121024.pdf","label":"IPSJ-CN24121024.pdf"},"date":[{"dateType":"Available","dateValue":"2026-01-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CN24121024.pdf","filesize":[{"value":"2.3 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"29"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"ab1cc970-46a2-4994-9066-3f6a74ba508a","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"高野, 紗輝"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中尾, 彰宏"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山口, 実靖"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小口, 正人"}],"nameIdentifiers":[{}]}]},"item_4_relation_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_relation_type_id":{"subitem_relation_type_select":"NCID","subitem_relation_type_id_text":"AB00006906"}}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2758-8262","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年スマートフォンなどのエッジデバイスで収集される個人情報を含むデータの活用が期待されている．しかし，Federated Learning をはじめ従来の分散機械学習分野の研究では，高性能な外部サーバが全てのデータまたは学習結果を集約・管理するため，情報漏洩等の脆弱性が指摘されている．この課題に対し，我々はエッジデバイスで得たデータおよび結果を外部へと一切受け渡さない選択が可能なプライバシ保護に優れた分散機械学習モデルを提案する．本論文では，エッジサーバでの学習をエッジデバイスで引き継ぎ，ユーザの許可を得た結果のみをエッジサーバで統合するモデルを提案する．エッジデバイスとして Jetson Nano を用いて実装した結果，エッジデバイス上では短時間で個人情報にも対応した結果を，エッジサーバ上では複数の学習結果を統合したより精度の高い結果をプライバシを保護しつつ得ることが可能であることが示された．本提案モデルを用いることでエッジデバイス上のデータを安全に効率よく活用することが可能となる．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告コラボレーションとネットワークサービス（CN）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-01-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"24","bibliographicVolumeNumber":"2024-CN-121"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}