Anomaly internet network traffic detection by kernel principle component classifier

Hanghang Tong; Chongrong Li; Jingrui He; Jiajian Chen; Quang Anh Tran; Haixin Duan; Xing Li

Anomaly internet network traffic detection by kernel principle component classifier

Hanghang Tong, Chongrong Li, Jingrui He, Jiajian Chen, Quang Anh Tran, Haixin Duan, Xing Li

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

As a crucial issue in computer network security, anomaly detection is receiving more and more attention from both application and theoretical point of view. In this paper, a novel anomaly detection scheme is proposed. It can detect anomaly network traffic which has extreme large value on some original feature by the major component, or does not follow the correlation structure of normal traffic by the minor component. By introducing kernel trick, the non-linearity of network traffic can be well addressed. To save the processing time, a simplified version is also proposed, where only major component is adopted. Experimental results validate the effectiveness of the proposed scheme.

Original language	English (US)
Title of host publication	Lecture Notes in Computer Science
Editors	J. Wang, X. Liao, Z. Yi
Pages	476-481
Number of pages	6
Volume	3498
Edition	III
State	Published - 2005
Externally published	Yes
Event	Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005 - Chongqing, China Duration: May 30 2005 → Jun 1 2005

Other

Other	Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005
Country/Territory	China
City	Chongqing
Period	5/30/05 → 6/1/05

ASJC Scopus subject areas

Computer Science (miscellaneous)

Cite this

@inproceedings{6331fdc8719b44c4bce69d3ccfee5a50,

title = "Anomaly internet network traffic detection by kernel principle component classifier",

abstract = "As a crucial issue in computer network security, anomaly detection is receiving more and more attention from both application and theoretical point of view. In this paper, a novel anomaly detection scheme is proposed. It can detect anomaly network traffic which has extreme large value on some original feature by the major component, or does not follow the correlation structure of normal traffic by the minor component. By introducing kernel trick, the non-linearity of network traffic can be well addressed. To save the processing time, a simplified version is also proposed, where only major component is adopted. Experimental results validate the effectiveness of the proposed scheme.",

author = "Hanghang Tong and Chongrong Li and Jingrui He and Jiajian Chen and Tran, {Quang Anh} and Haixin Duan and Xing Li",

year = "2005",

language = "English (US)",

volume = "3498",

pages = "476--481",

editor = "J. Wang and X. Liao and Z. Yi",

booktitle = "Lecture Notes in Computer Science",

edition = "III",

note = "Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005 ; Conference date: 30-05-2005 Through 01-06-2005",

}

TY - GEN

T1 - Anomaly internet network traffic detection by kernel principle component classifier

AU - Tong, Hanghang

AU - Li, Chongrong

AU - He, Jingrui

AU - Chen, Jiajian

AU - Tran, Quang Anh

AU - Duan, Haixin

AU - Li, Xing

PY - 2005

Y1 - 2005

N2 - As a crucial issue in computer network security, anomaly detection is receiving more and more attention from both application and theoretical point of view. In this paper, a novel anomaly detection scheme is proposed. It can detect anomaly network traffic which has extreme large value on some original feature by the major component, or does not follow the correlation structure of normal traffic by the minor component. By introducing kernel trick, the non-linearity of network traffic can be well addressed. To save the processing time, a simplified version is also proposed, where only major component is adopted. Experimental results validate the effectiveness of the proposed scheme.

AB - As a crucial issue in computer network security, anomaly detection is receiving more and more attention from both application and theoretical point of view. In this paper, a novel anomaly detection scheme is proposed. It can detect anomaly network traffic which has extreme large value on some original feature by the major component, or does not follow the correlation structure of normal traffic by the minor component. By introducing kernel trick, the non-linearity of network traffic can be well addressed. To save the processing time, a simplified version is also proposed, where only major component is adopted. Experimental results validate the effectiveness of the proposed scheme.

UR - http://www.scopus.com/inward/record.url?scp=24944518771&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24944518771&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:24944518771

VL - 3498

SP - 476

EP - 481

BT - Lecture Notes in Computer Science

A2 - Wang, J.

A2 - Liao, X.

A2 - Yi, Z.

T2 - Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005

Y2 - 30 May 2005 through 1 June 2005

ER -

Anomaly internet network traffic detection by kernel principle component classifier

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this