Presentation 2011-11-28
A Consideration of Regular Traffic Analysis in a Local Area Network
Jun SUGAHARA, Toyokazu AKIYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Understanding regular traffic is necessary to apply network anomaly detection methods. In this paper, we investigated the traffic parameter distribution of a Local Area Network (LAN). We use Gaussian Mixture Model approximation to analyze the difference in the number of packets and flows per unit time. As a result of the investigation, we confirmed the assumption of the distribution in the existing detection methods is not always applicable to the LAN. We also confirmed that the proposed analysis method can be more effective by extracting the target packets and store the captured packets to the DB.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) anomaly detection / EM algorithm / traffic analysis
Paper # IA2011-37
Date of Issue

Conference Information
Committee IA
Conference Date 2011/11/21(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) A Consideration of Regular Traffic Analysis in a Local Area Network
Sub Title (in English)
Keyword(1) anomaly detection
Keyword(2) EM algorithm
Keyword(3) traffic analysis
1st Author's Name Jun SUGAHARA
1st Author's Affiliation Kyoto Sangyo University()
2nd Author's Name Toyokazu AKIYAMA
2nd Author's Affiliation Kyoto Sangyo University
Date 2011-11-28
Paper # IA2011-37
Volume (vol) vol.111
Number (no) 321
Page pp.pp.-
#Pages 6
Date of Issue