Presentation 2012-11-22
A Classification Method of Application Traffic in Encrypted Tunnel Using SVM
ThanhTuan NGUYEN, Yasuhiro NAKAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Curently, research on classification of application traffic which use the result of monitoring network traffic with encrypted payload of packet has been proposed. They identify network traffic using methods that compare the characteristics of transmission and reception of unknown application flow and the known applications flow. However, in the case of network traffic of encrypted tunnel, it is difficult to split flow, packet transmission is delayed on the route and the changes in the behavior of each application is destabilizing. Thus, stable and hight accuracy idenification has been difficult. In this report, we extracted the feature vectors that eliminated influence of the delay on the Internet. We based on SVM (Support Vector Machines), one of the most promising Machine Learning (ML) tools, for apply to the problem of traffic classification in encrypted tunnel. Validation experiments result showed hight accuracy 90%~97%, although use only about 2~5 feature vectors.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) SVM / Network traffic / Classification / Application / Encryption
Paper # ISEC2012-64,LOIS2012-39
Date of Issue

Conference Information
Committee LOIS
Conference Date 2012/11/14(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 Life Intelligence and Office Information Systems (LOIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Classification Method of Application Traffic in Encrypted Tunnel Using SVM
Sub Title (in English)
Keyword(1) SVM
Keyword(2) Network traffic
Keyword(3) Classification
Keyword(4) Application
Keyword(5) Encryption
1st Author's Name ThanhTuan NGUYEN
1st Author's Affiliation Department of Computer Science National Defense Academy()
2nd Author's Name Yasuhiro NAKAMURA
2nd Author's Affiliation Department of Computer Science National Defense Academy
Date 2012-11-22
Paper # ISEC2012-64,LOIS2012-39
Volume (vol) vol.112
Number (no) 306
Page pp.pp.-
#Pages 5
Date of Issue