A New Intrusion Detection Method Based on BPSO-SVM

Author

Ma, Jing ; Liu, Xingwei ; Liu, Sijia

Author_Institution

Sch. of Math. & Comput. Eng., Xihua Univ., Chengdu

Volume

1

fYear

2008

fDate

17-18 Oct. 2008

Firstpage

473

Lastpage

477

Abstract

Intelligent algorithms being applied in intrusion detection system (IDS) becomes a tendency in recent years. This paper presents a new method of hybrid detection based on BPSO-SVM, a mixed algorithm that is composed of modified binary particle swarm optimization (BPSO) and support vector machine (SVM). This algorithm proposes a simultaneous feature selection and SVM parameters optimization. Experiments on KDD CUP´99 dataset show that this method can be an effective way for hybrid detection.

Keywords

particle swarm optimisation; security of data; support vector machines; BPSO-SVM; binary particle swarm optimization; computer systems; intelligent algorithms; intrusion detection method; support vector machine; Algorithm design and analysis; Computational intelligence; Computer networks; Design engineering; Intrusion detection; Machine intelligence; Mathematics; Particle swarm optimization; Support vector machine classification; Support vector machines; Binary PSO; Feature Selection; Intrusion Detection; Parameters Optimization; SVM;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Design, 2008. ISCID '08. International Symposium on

Conference_Location

Wuhan

Print_ISBN

978-0-7695-3311-7

Type

conf

DOI

10.1109/ISCID.2008.65

Filename

4725652