Presentation 2010-11-18
Network Application Identification using Observation Probability of Payload Length
Yuji WAIZUMI, Tsuyoshi SATO, Kazuyuki TANAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, increasing of information leakages caused by illegal use of network applications have been reported. To prevent the occurrence of such incidents, a network administrator should block the traffic exchanged by unauthorized applications by checking incoming and outgoing traffic of network. A simple application identification method utilizes port numbers. This method is based on an assumption that applications can be mapped to corresponding port numbers. However, this method is not effective because port number setting for applications can be change easily. Therefore, we need a method which quickly identification without port numbers, which are easily spoofed. In this report, we assume that same application flows have similar transition pattern of payload length of each packet in the first stage of connection, and propose a method to identify applications using observation probabilities of payload length.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Application / Identification / Payload Length / Transition pattern / Joint Probability
Paper # NC2010-53
Date of Issue

Conference Information
Committee NC
Conference Date 2010/11/11(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Network Application Identification using Observation Probability of Payload Length
Sub Title (in English)
Keyword(1) Application
Keyword(2) Identification
Keyword(3) Payload Length
Keyword(4) Transition pattern
Keyword(5) Joint Probability
1st Author's Name Yuji WAIZUMI
1st Author's Affiliation Graduate School of Information Sciences, Tohoku University()
2nd Author's Name Tsuyoshi SATO
2nd Author's Affiliation Graduate School of Information Sciences, Tohoku University
3rd Author's Name Kazuyuki TANAKA
3rd Author's Affiliation Graduate School of Information Sciences, Tohoku University
Date 2010-11-18
Paper # NC2010-53
Volume (vol) vol.110
Number (no) 295
Page pp.pp.-
#Pages 6
Date of Issue