{"id":224716,"updated":"2025-01-19T13:02:50.396415+00:00","links":{},"created":"2025-01-19T01:24:17.046099+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00224716","sets":["1164:3925:11156:11157"]},"path":["11157"],"owner":"44499","recid":"224716","title":["電子メール本文のベクトル化による本人確認手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-27"},"_buckets":{"deposit":"30f21ad8-ae25-4ff5-bf91-3153931bc29c"},"_deposit":{"id":"224716","pid":{"type":"depid","value":"224716","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"電子メール本文のベクトル化による本人確認手法","author_link":["593149","593151","593146","593145","593150","593158","593157","593148","593155","593154","593147","593152","593156","593153"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"電子メール本文のベクトル化による本人確認手法"},{"subitem_title":"Verification of Users by Vectorizing E-mail Bodies","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"個人識別","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-02-27","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京工科大学"},{"subitem_text_value":"東京工科大学"},{"subitem_text_value":"東京工科大学"},{"subitem_text_value":"東京工科大学"},{"subitem_text_value":"東京工科大学"},{"subitem_text_value":"東京工科大学"},{"subitem_text_value":"東京工科大学"}]},"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/224716/files/IPSJ-CSEC23100040.pdf","label":"IPSJ-CSEC23100040.pdf"},"date":[{"dateType":"Available","dateValue":"2025-02-27"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CSEC23100040.pdf","filesize":[{"value":"270.6 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":"44"}],"accessrole":"open_date","version_id":"a7f44616-0b55-48ee-9ca7-f54ae1a1b410","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"下里, 賢司"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"望月, 郁弥"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"行田, 早希"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小林, 亮"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山田, 悠人"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"西村, 彩夏"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"宇田, 隆哉"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kenji, Shimosato","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Fumiya, Mochizuki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Saki, Kouda","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Ryo, Kobayashi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuto, Yamada","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Ayaka, Nishimura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Ryuya, Uda","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11235941","subitem_source_identifier_type":"NCID"}]},"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":"2188-8655","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"我々が日々受信する Email の中には不適切なものが常に含まれている.既存のメールフィルタシステムでは,本文中に添付されている URL やアドレスを基に適切であるかどうか判別しているものがある.しかし,不正アクセスによってメールアドレスが奪われ,第三者からなりすましのメールを送られた場合には対応できない.そこで,本研究では,単語の分散表現と分布仮説を組み合わせた機械学習システムを用いて,英語で記述された電子メールの本文から特徴の抽出を試みた.メール本文の前処理として,メールのアカウント所持者から送信されたメール群となりすましメール群をそれぞれ Word2Vec を用いて単語ごとにベクトル化し,機械学習を行った.機械学習アルゴリズムには CNN,SVM,RF をそれぞれ用い,本人かそうでないかの 2 値分類を行った.分類の結果,Scoreは,CNN が 0.758,SVM が 0.834,RF が 0.844 となった.今回の実験では,1 名あたり 100 件,合計 3,000 件のメールしか扱っていないため精度がこの程度となったが,データ量を増やせば,なりすましメール対策用のメールフィルタシステムを構築できる可能性はある.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータセキュリティ(CSEC)"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-27","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"40","bibliographicVolumeNumber":"2023-CSEC-100"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}