Intrusion detection using an ensemble of intelligent paradigms

被引：202

作者：

Mukkamala, S ^{[1
]}

Sung, AH

Abraham, A

机构：

[1] New Mexico Inst Min & Technol, Dept Comp Sci, Socorro, NM 87801 USA

[2] Oklahoma State Univ, Dept Comp Sci, Tulsa, OK USA

来源：

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS | 2005年 / 28卷 / 02期

基金：

美国国家科学基金会;

关键词：

computer security; support vector machines; network security;

D O I：

10.1016/j.jnca.2004.01.003

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Soft computing techniques are increasingly being used for problem solving. This paper addresses using an ensemble approach of different soft computing and hard computing techniques for intrusion detection. Due to increasing incidents of cyber attacks, building effective intrusion detection systems are essential for protecting information systems security, and yet it remains an elusive goal and a great challenge. We studied the performance of Artificial Neural Networks (ANNs), Support Vector Machines (SVMs) and Multivariate Adaptive Regression Splines (MARS). We show that an ensemble of ANNs, SVMs and MARS is superior to individual approaches for intrusion detection in terms of classification accuracy. (C) 2004 Elsevier Ltd. All rights reserved.

引用

页码：167 / 182

页数：16