機械学習の手法を用いたメタデータによるマルウェアの高速な分類方法

• Item type: Symposium(1)
• 公開日: 2011-10-12
• タイトル: 機械学習の手法を用いたメタデータによるマルウェアの高速な分類方法
• タイトル / 言語: en
• タイトル: An approach to fast malware classification based on malware's meta-data using machine learning technique
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: コンピュータウィルス（２）
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_5794
• 資源タイプ: conference paper
• 著者所属: Faculty of Environmental Information, Keio University
• 著者所属: Faculty of Environmental Information, Keio University
• 著者所属: Graduate School of Media and Governance, Keio University
• 著者所属: Faculty of Environmental Information, Keio University
• 著者所属(英): en
• 著者所属(英): Faculty of Environmental Information, Keio University
• 著者所属(英): en
• 著者所属(英): Faculty of Environmental Information, Keio University
• 著者所属(英): en
• 著者所属(英): Graduate School of Media and Governance, Keio University
• 著者所属(英): en
• 著者所属(英): Faculty of Environmental Information, Keio University
• 著者名: PhamVanHung; Toshinori, Usui; Kunihiko, Shigematsu; Keiji, Takeda
• 著者名(英): Pham, VanHung; Toshinori, Usui; Kunihiko, Shigematsu; Keiji, Takeda
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: With the rapid increase in malware, it is important for malware analysis that classifying unknown malware files into malware families to characterize the type of behavior and static malware characteristic accuracy. In this paper we introduce an approach to fast malware classification based on malware's file meta-data. We used a machine learning technique called decision tree algorithm to classify malware rapidly and correctly. Experimental results with the malware samples show that our system successfully determined some semantic similarity between malware and showed their inner similarity in behavior and static malware characteristic.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: With the rapid increase in malware, it is important for malware analysis that classifying unknown malware files into malware families to characterize the type of behavior and static malware characteristic accuracy. In this paper we introduce an approach to fast malware classification based on malware's file meta-data. We used a machine learning technique called decision tree algorithm to classify malware rapidly and correctly. Experimental results with the malware samples show that our system successfully determined some semantic similarity between malware and showed their inner similarity in behavior and static malware characteristic.
• 書誌情報: コンピュータセキュリティシンポジウム2011 論文集; 巻 2011, 号 3, p. 792-796, 発行日 2011-10-12
• 出版者 / 言語: ja
• 出版者: 情報処理学会