Gradient Boosting Decision Tree Ensemble Learning for Malware Binary Classification

• Item type: Symposium(1)
• 公開日: 2020-10-19
• タイトル: Gradient Boosting Decision Tree Ensemble Learning for Malware Binary Classification
• タイトル / 言語: en
• タイトル: Gradient Boosting Decision Tree Ensemble Learning for Malware Binary Classification
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: malware classification，machine learning，ensemble learning
• 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: Graduate School of Informatics, Nagoya University
• 著者所属: Information Strategy Office, Nagoya University
• 著者所属: Information Technology Center, Nagoya University
• 著者所属: Information Technology Center, Nagoya University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Nagoya University
• 著者所属(英): en
• 著者所属(英): Information Strategy Office, Nagoya University
• 著者所属(英): en
• 著者所属(英): Information Technology Center, Nagoya University
• 著者所属(英): en
• 著者所属(英): Information Technology Center, Nagoya University
• 著者名: Yun, Gao; Hirokazu, Hasegawa; Yukiko, Yamaguchi; Hajime, Shimada
• 著者名(英): Yun, Gao; Hirokazu, Hasegawa; Yukiko, Yamaguchi; Hajime, Shimada
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: The increasing number of malicious software spread through the Internet has become a serious threat. Malware authors use obfuscation and deformation techniques to generate new types of malware in order to evade the detection of traditional detection methods, so that it is widely expected for machine learning methods that classifies malware and cleanware based on the characteristics of the samples. The current research trend is to use machine learning technology, especially decision tree technology, to identify new malicious software quickly and accurately. The purpose of this paper is to investigate malware classification accuracy based on latest decision tree based algorithms including ensemble learning. Therefore, we use the FFRI Dataset 2019 to construct malware detection models from surface analysis logs and PE header dumps. We have successfully developed a malware detection model that is more accurate than previous studies. We have obtained good classification results using only 27 features.
• 書誌情報: コンピュータセキュリティシンポジウム2020論文集; p. 589-595, 発行日 2020-10-19
• 出版者 / 言語: ja
• 出版者: 情報処理学会