Presentation 2010-11-24
高精度なネットワーク侵入検知システムの構築(学生セッション,学生セッション,一般)
Moriteru ISHIDA, Hiroki TAKAKURA, Yasuo OKABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Intrusion detection systems(IDSs) are important equipments for network security. Recently, there's been an emerging research on them and especially several studies have focused on anomaly based IDSs using unsupervised machine learning techniques. However past studies still haven't overcome two problems, i.e., low detection rate and high false positive rate. In addition, there is a problem that past reserches haven' t been evaluated with real traffic data. In order to solve them, we propose an application of the clustering algorithm based on OptiGrid to IDS and an improvement of the existing cluster-labeling method. We also evaluate our system with both KDDCUP1999 data and real traffic data collected by honeypots in Kyoto University.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) intrusion detection system / IDS / anomaly detection / clustering / OptiGrid
Paper # IA2010-56
Date of Issue

Conference Information
Committee IA
Conference Date 2010/11/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Internet Architecture(IA)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English)
Sub Title (in English)
Keyword(1) intrusion detection system
Keyword(2) IDS
Keyword(3) anomaly detection
Keyword(4) clustering
Keyword(5) OptiGrid
1st Author's Name Moriteru ISHIDA
1st Author's Affiliation Guraduate School of Informatics, Kyoto University()
2nd Author's Name Hiroki TAKAKURA
2nd Author's Affiliation Information Technology Center, Nagoya University
3rd Author's Name Yasuo OKABE
3rd Author's Affiliation Academic Center for Computing and Media Studies, Kyoto University
Date 2010-11-24
Paper # IA2010-56
Volume (vol) vol.110
Number (no) 304
Page pp.pp.-
#Pages 6
Date of Issue