Presentation 2004/10/15
Improving Accuracy of Network-based Anomaly Detection Using Multiple Detection Modules
Yohei SATO, Yuji WAIZUMI, Yoshiaki NEMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Accuracy of anomaly-based intrusion detection depends on used features obtained from network traf- fic. Therefore, use of appropriate features that suited to each type of anomalous event is necessary for improving accuracy of the detection. In this paper, we describe that an anomaly affects specific features according to its char- acteristics. Then, we propose the intrusion detetction system consist of multiple detection modules. Each module uses different features to detect different type of anomalies. In addition, effectiveness of the proposed system is shown through experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Anomaly Detection / Improving Accuracy / Features / Principal Component Analysis(PCA)
Paper # NS2004-144
Date of Issue

Conference Information
Committee NS
Conference Date 2004/10/15(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 Network Systems(NS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Improving Accuracy of Network-based Anomaly Detection Using Multiple Detection Modules
Sub Title (in English)
Keyword(1) Anomaly Detection
Keyword(2) Improving Accuracy
Keyword(3) Features
Keyword(4) Principal Component Analysis(PCA)
1st Author's Name Yohei SATO
1st Author's Affiliation Graduate School of Information Sciences, TOHOKU University()
2nd Author's Name Yuji WAIZUMI
2nd Author's Affiliation Graduate School of Information Sciences, TOHOKU University
3rd Author's Name Yoshiaki NEMOTO
3rd Author's Affiliation Graduate School of Information Sciences, TOHOKU University
Date 2004/10/15
Paper # NS2004-144
Volume (vol) vol.104
Number (no) 354
Page pp.pp.-
#Pages 4
Date of Issue