{"created":"2025-01-19T01:45:29.837297+00:00","updated":"2025-03-06T06:11:53.088838+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00240990","sets":["6164:6165:6462:11854"]},"path":["11854"],"owner":"11","recid":"240990","title":["高次元クエリに対するStaircaseメカニズムの適用"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2024-10-15"},"_buckets":{"deposit":"63f50f96-23c4-417e-a33c-a8ebdd569cac"},"_deposit":{"id":"240990","pid":{"type":"depid","value":"240990","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"高次元クエリに対するStaircaseメカニズムの適用","author_link":["662652","662653","662654","662655","662656","662657","662658","662659","662660","662661","662662","662663","662664","662665","662666","662667","662668","662669"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"高次元クエリに対するStaircaseメカニズムの適用","subitem_title_language":"ja"},{"subitem_title":"Staircase Mechanism for High-dimensional Queries","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"差分プライバシー，Staircase メカニズム，Laplace メカニズム，平均絶対誤差","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2024-10-15","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":"NTT社会情報研究所"},{"subitem_text_value":"株式会社アーク情報システム"},{"subitem_text_value":"株式会社アーク情報システム"},{"subitem_text_value":"NTT社会情報研究所"},{"subitem_text_value":"NTT社会情報研究所"},{"subitem_text_value":"NTT社会情報研究所"},{"subitem_text_value":"NTT社会情報研究所"},{"subitem_text_value":"NTTテクノクロス株式会社"},{"subitem_text_value":"群馬大学"}]},"item_18_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"NTT Social Informatics Laboratories","subitem_text_language":"en"},{"subitem_text_value":"ARK Information Systems, INC.","subitem_text_language":"en"},{"subitem_text_value":"ARK Information Systems, INC.","subitem_text_language":"en"},{"subitem_text_value":"NTT Social Informatics Laboratories","subitem_text_language":"en"},{"subitem_text_value":"NTT Social Informatics Laboratories","subitem_text_language":"en"},{"subitem_text_value":"NTT Social Informatics Laboratories","subitem_text_language":"en"},{"subitem_text_value":"NTT Social Informatics Laboratories","subitem_text_language":"en"},{"subitem_text_value":"NTT TechnoCross Corporation","subitem_text_language":"en"},{"subitem_text_value":"Gunma University","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/240990/files/IPSJ-CSS2024244.pdf","label":"IPSJ-CSS2024244.pdf"},"date":[{"dateType":"Available","dateValue":"2026-10-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CSS2024244.pdf","filesize":[{"value":"569.0 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":"95951a5b-f465-4c98-bdaa-62e6cea72350","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"三浦, 尭之"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"竹内, 弘史"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"櫛部, 義幸"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"紀伊, 真昇"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"芝原, 俊樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山本, 充子"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"市川, 敦謙"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"石原, 一郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"千田, 浩司"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takayuki, Miura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Takeuchi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yoshiyuki, Kushibe","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Masanobu, Kii","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Toshiki, Shibahara","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Juko, Yamamoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Atsunori, Ichikawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Ichiro, Ishihara","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Koji, Chida","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":"Staircaseメカニズムは，差分プライバシー分野で標準的に用いられるLaplaceメカニズムをより精緻にしたものであり，出力次元が2次元の場合までは平均絶対誤差が最適となることがGengらによって理論的に示されている．しかし，その誤差は具体的な数値による評価ができる記述ではなく，高次元の場合に関しては実用価値があるのかの判断ができなかった．本研究では，高次元Staircaseメカニズムを具体的な数値で解析可能にし，集計表などを作るクエリに対して従来の高次元Staircaseメカニズムよりも誤差が小さくなるComponent-wise Staircaseメカニズムという手法を提案する．また，その有用性解析に必要な近似計算の実用的な方法も提案した．それらを用いた数値計算によって，高次元StaircaseメカニズムがLaplaceメカニズムより優れている条件を明らかにし，提案手法のComponent-wise Staircaseメカニズムが従来の高次元Staircaseメカニズムより優れていることを示した．","subitem_description_type":"Other"}]},"item_18_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The Staircase mechanism is a more sophisticated mechanism of the Laplace mechanism that is standard in differential privacy, and Geng et al. theoretically showed that the mean absolute error is optimal in the case that the output dimension is two. However, it was not possible to determine whether it is practical for high dimensionality. In this study, we propose a component-wise staircase mechanism that enables us to analyze the high-dimensional staircase mechanism with concrete numerical values, and that has a smaller error than the conventional high-dimensional staircase mechanism for queries that create tabulation tables. We also propose a practical computation necessary to analyze the utility of the mechanism. Numerical experiments reveal the conditions under which the higher-dimensional Staircase mechanism is superior to the Laplace mechanism. The proposed component-wise Staircase mechanism is superior to the conventional high-dimensional Staircase mechanism. ","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"1838","bibliographic_titles":[{"bibliographic_title":"コンピュータセキュリティシンポジウム2024論文集"}],"bibliographicPageStart":"1831","bibliographicIssueDates":{"bibliographicIssueDate":"2024-10-15","bibliographicIssueDateType":"Issued"}}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":240990,"links":{}}