Research of the network intrusion detection method based on support vector machine

Ying Tang; Lixin Xu

doi:10.1117/12.791498

Research of the network intrusion detection method based on support vector machine

Ying Tang^*, Lixin Xu

^*Corresponding author for this work

School of Mechatronical Engineering

Beijing Institute of Technology

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

Abstract

For the growing web intrusion issues, we propose a new method for intrusion detection. In this paper, statistical learning theory (SLT) is introduced to intrusion detection and a method based on support vector machine (SVM) is presented. Theory of SVM is introduced first, and then in data pretreatment, we propose a method of reducing the dimension of primal data sets and a method of transforming eigenvalue from characters to numbers. In virtue of the network data sets which appear variable, small and with high dimension, we introduce the Sequential Minimal Optimization (SMO) algorithm which is especially for large scale problems. The testing result based on the DARPA data show that the method is effective and efficient.

Original language	English
Title of host publication	International Symposium on Photoelectronic Detection and Imaging 2007 - Image Processing
DOIs	https://doi.org/10.1117/12.791498
Publication status	Published - 2008
Event	International Symposium on Photoelectronic Detection and Imaging 2007 - Image Processing - Beijing, China Duration: 9 Sept 2007 → 12 Sept 2007

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	6623
ISSN (Print)	0277-786X

Conference

Conference	International Symposium on Photoelectronic Detection and Imaging 2007 - Image Processing
Country/Territory	China
City	Beijing
Period	9/09/07 → 12/09/07

Keywords

Internet security
Intrusion detection
Kernel function
Pattern recognition
SMO
Statistical learning theory
Support vector machine

Access to Document

10.1117/12.791498

Cite this

Tang, Y., & Xu, L. (2008). Research of the network intrusion detection method based on support vector machine. In International Symposium on Photoelectronic Detection and Imaging 2007 - Image Processing Article 662318 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6623). https://doi.org/10.1117/12.791498

@inproceedings{82d287fba38a45afbd2679370bb56b2d,

title = "Research of the network intrusion detection method based on support vector machine",

abstract = "For the growing web intrusion issues, we propose a new method for intrusion detection. In this paper, statistical learning theory (SLT) is introduced to intrusion detection and a method based on support vector machine (SVM) is presented. Theory of SVM is introduced first, and then in data pretreatment, we propose a method of reducing the dimension of primal data sets and a method of transforming eigenvalue from characters to numbers. In virtue of the network data sets which appear variable, small and with high dimension, we introduce the Sequential Minimal Optimization (SMO) algorithm which is especially for large scale problems. The testing result based on the DARPA data show that the method is effective and efficient.",

keywords = "Internet security, Intrusion detection, Kernel function, Pattern recognition, SMO, Statistical learning theory, Support vector machine",

author = "Ying Tang and Lixin Xu",

year = "2008",

doi = "10.1117/12.791498",

language = "English",

isbn = "9780819467652",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

booktitle = "International Symposium on Photoelectronic Detection and Imaging 2007 - Image Processing",

note = "International Symposium on Photoelectronic Detection and Imaging 2007 - Image Processing ; Conference date: 09-09-2007 Through 12-09-2007",

}

Tang, Y & Xu, L 2008, Research of the network intrusion detection method based on support vector machine. in International Symposium on Photoelectronic Detection and Imaging 2007 - Image Processing., 662318, Proceedings of SPIE - The International Society for Optical Engineering, vol. 6623, International Symposium on Photoelectronic Detection and Imaging 2007 - Image Processing, Beijing, China, 9/09/07. https://doi.org/10.1117/12.791498

Research of the network intrusion detection method based on support vector machine. / Tang, Ying; Xu, Lixin.
International Symposium on Photoelectronic Detection and Imaging 2007 - Image Processing. 2008. 662318 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6623).

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

TY - GEN

T1 - Research of the network intrusion detection method based on support vector machine

AU - Tang, Ying

AU - Xu, Lixin

PY - 2008

Y1 - 2008

N2 - For the growing web intrusion issues, we propose a new method for intrusion detection. In this paper, statistical learning theory (SLT) is introduced to intrusion detection and a method based on support vector machine (SVM) is presented. Theory of SVM is introduced first, and then in data pretreatment, we propose a method of reducing the dimension of primal data sets and a method of transforming eigenvalue from characters to numbers. In virtue of the network data sets which appear variable, small and with high dimension, we introduce the Sequential Minimal Optimization (SMO) algorithm which is especially for large scale problems. The testing result based on the DARPA data show that the method is effective and efficient.

AB - For the growing web intrusion issues, we propose a new method for intrusion detection. In this paper, statistical learning theory (SLT) is introduced to intrusion detection and a method based on support vector machine (SVM) is presented. Theory of SVM is introduced first, and then in data pretreatment, we propose a method of reducing the dimension of primal data sets and a method of transforming eigenvalue from characters to numbers. In virtue of the network data sets which appear variable, small and with high dimension, we introduce the Sequential Minimal Optimization (SMO) algorithm which is especially for large scale problems. The testing result based on the DARPA data show that the method is effective and efficient.

KW - Internet security

KW - Intrusion detection

KW - Kernel function

KW - Pattern recognition

KW - SMO

KW - Statistical learning theory

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=43249099131&partnerID=8YFLogxK

U2 - 10.1117/12.791498

DO - 10.1117/12.791498

M3 - Conference contribution

AN - SCOPUS:43249099131

SN - 9780819467652

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - International Symposium on Photoelectronic Detection and Imaging 2007 - Image Processing

T2 - International Symposium on Photoelectronic Detection and Imaging 2007 - Image Processing

Y2 - 9 September 2007 through 12 September 2007

ER -

Research of the network intrusion detection method based on support vector machine

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this