{"id":175745,"updated":"2025-01-20T06:10:42.595388+00:00","links":{},"created":"2025-01-19T00:45:29.007952+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00175745","sets":["6164:6165:6462:8948"]},"path":["8948"],"owner":"11","recid":"175745","title":["Paragraph Vectorを用いたマルウェアの亜種推定法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2016-10-04"},"_buckets":{"deposit":"0a7e773b-b60c-4b25-9512-15fc08924aa8"},"_deposit":{"id":"175745","pid":{"type":"depid","value":"175745","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"Paragraph Vectorを用いたマルウェアの亜種推定法","author_link":["367518","367517","367519","367515","367520","367516"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Paragraph Vectorを用いたマルウェアの亜種推定法"},{"subitem_title":"Detectiong Malware Variants Using Paragraph Vector","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"亜種マルウェア，動的解析，APIコール，Deep Learning，Paragraph Vector","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2016-10-04","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":"早稲田大学"},{"subitem_text_value":"早稲田大学"},{"subitem_text_value":"早稲田大学"}]},"item_18_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Waseda 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/175745/files/IPSJCSS2016045.pdf","label":"IPSJCSS2016045.pdf"},"date":[{"dateType":"Available","dateValue":"2018-10-04"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJCSS2016045.pdf","filesize":[{"value":"835.6 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":"46"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"fb2b4654-af85-4835-941a-aca0fa9b0bfa","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2016 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"佐藤, 拓未"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"後藤, 滋樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"武部, 嵩礼"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takumi, Sato","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shigeki, Goto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takanori, Takebe","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_18_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":"ISSN　1882-0840"}}]},"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":"マルウェアの亜種はツールを用いることで容易に作成可能である．マルウェアの亜種の発見数が顕著に増加している．マルウェアの種別に応じた適切な対策のためには，効率のよい亜種の判定が望まれる．本研究は，マルウェアの動的解析の結果に含まれる API コール群を用いて，マルウェアが指定の亜種であるかどうかを推定する．具体的には，マルウェアが呼び出す API 群およびその引数に着目し，それらを自然言語の一連の文章のように捉えて Deep Learning の技術を用いて Paragraph Vector を作成する．自然言語における文脈の特徴に相当する情報を動的解析から導く．提案手法により人間による特徴の選定および抽出を行わない自動的なマルウェアの亜種判定を実現する．","subitem_description_type":"Other"}]},"item_18_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Subspecific malware, or a malware variant, can be easily made by tools. The number of subspecific malware is increasing remarkably. For appropriate countermeasures for a malware family, it is desirable to realize an effective method for deciding subspecific malware in a family. This paper proposes a new method for determine malware variants. We use log files of dynamic analysis of malware in FFRI Dataset. We focus on API calls and their arguments. Our method treat them as a natural language sentence. We apply Deep Learning technology, and convert log files into Paragraph Vectors.  The paragraph vector represents a  feature vector, which characterize malware variants.  The proposed method does not depend on manual extraction of malware features by human observation.","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"304","bibliographic_titles":[{"bibliographic_title":"コンピュータセキュリティシンポジウム2016論文集"}],"bibliographicPageStart":"298","bibliographicIssueDates":{"bibliographicIssueDate":"2016-10-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"2016"}]},"relation_version_is_last":true,"weko_creator_id":"11"}}