Identifying important features for intrusion detection using support vector machines and neural networks

被引：193

作者：

Sung, AH ^{[1
]}

Mukkamala, S ^{[1
]}

机构：

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

来源：

2003 SYMPOSIUM ON APPLICATIONS AND THE INTERNET, PROCEEDINGS | 2003年

关键词：

D O I：

10.1109/SAINT.2003.1183050

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Intrusion detection is a critical component of secure information systems. This paper addresses the issue of identifying important input features in building an intrusion detection system (IDS). Since elimination of the insignificant and/or useless inputs leads to a simplification of the problem, faster and more accurate detection may result. Feature ranking and selection, therefore, is an important issue in intrusion detection. In this paper we apply the technique of deleting one feature at a time to perform experiments on SVMs and neural networks to rank the importance of input features for the DARPA collected intrusion data. Important features for each of the 5 classes of intrusion patterns in the DARPA data are identified. It is shown that SVM-based and neural network based IDSs using a reduced number of features can deliver enhanced or comparable performance. An IDS for class-specific detection based on five SVMs is proposed.

引用

页码：209 / 216

页数：8