Title: An efficient intrusion detection system using a boosting-based learning algorithm

Authors: Zhenwei Yu, Jeffrey J.P. Tsai

Addresses: Department of Computer Science, University of Illinois at Chicago, 851 S Morgan St., Room 1120 SEO, IL 60607, Chicago, USA. ' Department of Computer Science, University of Illinois at Chicago, 851 S Morgan St., Room 1120 SEO, IL 60607, Chicago, USA

Abstract: Boosting is effective in improving the accuracy of a learner. In this paper, we present our research in developing a Multi-Class SLIPPER (MC-SLIPPER) system for intrusion detection from a boosting-based learning algorithm. Our system is built from multiple available binary SLIPPER modules. Multiple prediction-confidence based strategies are proposed and applied to arbitrate the final prediction among predictions from all binary SLIPPER modules. Our MC-SLIPPER system is evaluated on the KDDCUP|99 intrusion detection dataset. The experimental results show that the system achieves the best performance using the BP neural network. And the system using other prediction strategies gets better performance than the winner of the KDDCUP|99 contest does in term of misclassification cost.

Keywords: BP neural networks; boosting algorithms; intrusion detection; KDDCUP|99 contest; misclassification cost; prediction confidence; learning algorithms; data mining.

DOI: 10.1504/IJCAT.2006.011994

International Journal of Computer Applications in Technology, 2006 Vol.27 No.4, pp.223 - 231

Published online: 08 Jan 2007 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article