Intrusion detection using neural network committee machine

Author

Husagic-Selman, Alma ; Koker, Rasit ; Selman, Suvad

Author_Institution

Dept. of Comput. Sci. & Eng., Int. Univ. of Sarajevo, Sarajevo, Bosnia-Herzegovina

fYear

2013

fDate

Oct. 30 2013-Nov. 1 2013

Firstpage

1

Lastpage

6

Abstract

Intrusion detection plays an important role in todays computer and communication technology. As such it is very important to design time efficient Intrusion Detection System (IDS) low in both, False Positive Rate (FPR) and False Negative Rate (FNR), but high in attack detection precision. To achieve that, this paper proposes Neural Network Committee Machine (NNCM) IDS. NNCM IDS consists of Input Reduction System based on Principal Component Analysis (PCA) and Intrusion Detection System, which is represented by three levels committee machine, each based on Back-Propagation Neural Network. To reduce the FNR, the system uses offline System Update, which retrains the networks when new attacks are introduced. The system shows the overall attack detection success of 99.8%.

Keywords

backpropagation; computer network security; neural nets; principal component analysis; FNR; FPR; NNCM IDS; PCA; attack detection precision; backpropagation neural network; communication technology; computer technology; false negative rate; false positive rate; input reduction system; intrusion detection system; neural network committee machine; offline system update; principal component analysis; Artificial neural networks; Biological neural networks; Intrusion detection; Neurons; Principal component analysis; Training; Committee Machine; Intelligent Intrusion Detection System; Intrusion detection; Neural Networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Information, Communication and Automation Technologies (ICAT), 2013 XXIV International Symposium on

Conference_Location

Sarajevo

Type

conf

DOI

10.1109/ICAT.2013.6684073

Filename

6684073