{"links":{},"id":2009650,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:02009650","sets":["1164:4088:1771221559804:1777431367596"]},"path":["1777431367596"],"owner":"80578","recid":"2009650","title":["IDSフューショット学習における量子機械学習の有効性について"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2026-05-21"},"_buckets":{"deposit":"e9ba84cb-13f0-4267-ba7d-c5ed7c09a64e"},"_deposit":{"id":"2009650","pid":{"type":"depid","value":"2009650","revision_id":0},"owners":[80578],"status":"published","created_by":80578},"item_title":"IDSフューショット学習における量子機械学習の有効性について","author_link":[],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"IDSフューショット学習における量子機械学習の有効性について","subitem_title_language":"ja"},{"subitem_title":"Effectiveness of Quantum Machine Learning in IDS Few-Shot Learning","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"CSEC","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2026-05-21","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"金沢大学"},{"subitem_text_value":"金沢大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Kanazawa University","subitem_text_language":"en"},{"subitem_text_value":"Kanazawa 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/2009650/files/IPSJ-IOT26073005.pdf","label":"IPSJ-IOT26073005.pdf"},"date":[{"dateType":"Available","dateValue":"2028-05-21"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-IOT26073005.pdf","filesize":[{"value":"1.1 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":"43"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"54d074b0-fdeb-475c-a6ff-9c19b14fe876","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2026 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"渡部,佑"}]},{"creatorNames":[{"creatorName":"満保,雅浩"}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12326962","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":"2188-8787","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"量子機械学習は，古典機械学習より柔軟で幅広い特徴表現を行える可能性が期待されているものの，その有用性が発揮される適用対象や方式について解明されていないことも多い．本論文では，学習サンプル数が少ない環境でのIoTの侵入検知システム（IDS）に対し，量子機械学習を適用し，その結果を考察する．具体的には，量子カーネルを用いたサポートベクターマシン（QSVM）を複数の設計で構築し，それらのQSVMおよび従来の古典的手法（古典SVM）と比較することで，分類性能を評価する．さらに，量子カーネル行列の固有値分布に着目し，特徴空間におけるデータ表現の違いと分類性能との関係について分析を行う．これにより，少数サンプル環境における量子機械学習の有用性および特性を明らかにすることを目的とする．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Quantum machine learning is expected to offer more flexible and broader feature representations than classical machine learning, but there are still many aspects regarding the specific applications and methods in which its utility can be fully realized that have not yet been clarified. In this paper, we apply quantum machine learning to an IoT intrusion detection system (IDS) operating in an environment with a few shot of training samples and discuss the results. Specifically, we construct quantum kernel-based support vector machines (QSVMs) with multiple designs and evaluate these classification performance and comparing them with conventional classical method (classical SVM). Furthermore, by focusing on the eigenvalues distribution of the quantum kernel matrix, we analyze the relationship between differences in data representation in the feature space and classification performance. The aim is to clarify the usefulness and characteristics of quantum machine learning in few shot environments.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"研究報告インターネットと運用技術（IOT）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2026-05-21","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"5","bibliographicVolumeNumber":"2026-IOT-73"}]},"relation_version_is_last":true,"weko_creator_id":"80578"},"created":"2026-05-14T07:16:26.782039+00:00","updated":"2026-05-14T07:16:32.244407+00:00"}