An intellectual anti-malware scheme using advanced sequence analysis techniques
Project/Area Number |
24700084
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Computer system/Network
|
Research Institution | National Institute of Information and Communications Technology |
Principal Investigator |
BAN Tao 独立行政法人情報通信研究機構, ネットワークセキュリティ研究所・サイバーセキュリティ研究室, 主任研究員 (80462878)
|
Project Period (FY) |
2012-04-01 – 2015-03-31
|
Project Status |
Completed (Fiscal Year 2014)
|
Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2014: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2013: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2012: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
Keywords | マルウェア解析 / 配列解析 / パッカー特定 / サポートベクトルマシン / カーネル関数 / スパムメール / サイバーセキュリティ / 機械学習 / スパムメール解析 / 分類器 / サポートベクターマシン / スペクトラムカーネル / アメリカ / イスラエル / ニュージーランド |
Outline of Final Research Achievements |
Research and development on computational intelligence techniques based on advanced sequence analysis are pursued in the aim of an analysis system that can detect polymorphic malware programs with good accuracy and efficiency. The newly proposed edit distance kernel function and spectrum kernel function make it possible to quantitatively evaluate the degree of similarity between sequences. Incorporating these kernel functions to the state-of-the-art classifiers, such as the support vector machine, renders the creation of a practical malware detection system possible. The proposed methods are evaluated using a database comprised of obfuscated programs generated by 25 types of packers. Their effectiveness and efficiency are illustrated by prediction accuracies over 99% and very quick system response time.
|
Report
(4 results)
Research Products
(17 results)
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] Smart Task Orderings for Active Online Multitask Learning2014
Author(s)
Shaoning Pang, Jianbei An, Jane Zhao, Xiaosong Li, Tap Ban, Daisuke Inoue, Adolhossein Sarrafzadeh
Organizer
SIAM International Conference on Data Mining 2014 (SDM 2014 Workshop on Heterogeneous Learning)
Place of Presentation
Philadelphia, Pennsylvania, USA
Year and Date
2014-04-24 – 2014-04-26
Related Report
-
-
-
-
-