2015 Fiscal Year Final Research Report
Effective detection of various kinds of cyberattacks using histogram database technology
Project/Area Number |
25330131
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Multimedia database
|
Research Institution | Kyushu University |
Principal Investigator |
Feng Yaokai 九州大学, システム情報科学研究科(研究院, 助教 (60363389)
|
Project Period (FY) |
2013-04-01 – 2016-03-31
|
Keywords | 分散型攻撃 / 挙動に基づく異常検知 / サイバーセキュリティ / ポートスキャン攻撃 |
Outline of Final Research Achievements |
1) For detecting many kinds of cyber attacks, features and machine learning algorithms were tested and their detection performance was verified. Specifically, DRDoS attacks, DNS amp attacks, the sign of DDoS attacks. 2) Histogram construction method was investigated by further detailed analysis of the behavior of the cyber attacks that have been collected. The performance was also demonstrated. 3) In order to dynamically and rapidly construct histogram in real time from large, multidimensional packet datasets was invesitgated. To accomplish an effective and rapid abnormality detection system, it is necessary to construct dynamically a moving histogram at high speed. We developed a method to incrementally construct histograms.
|
Free Research Field |
ネットワークセキュリティ
|