A detailed analysis of classifier ensembles for intrusion detection in wireless network

被引：7

作者：

Tama, Bayu Adhi ^{[1
,2
]}

Rhee, Kyung-Hyune ^{[2
]}

机构：

[1] Laboratory of Information Security and Internet Applications, Pukyong National University, Busan, Korea, Republic of

[2] Faculty of Computer Science, Sriwijaya University, Inderalaya, Ogan Ilir, Sumatera Selatan, Indonesia

来源：

Journal of Information Processing Systems | 2017年 / 13卷 / 05期

基金：

新加坡国家研究基金会;

关键词：

Computer crime - IEEE Standards - Intrusion detection - Support vector machines - Data mining - Decision trees;

D O I：

10.3745/JIPS.03.0080

中图分类号：

学科分类号：

摘要：

Intrusion detection systems (IDSs) are crucial in this overwhelming increase of attacks on the computing infrastructure. It intelligently detects malicious and predicts future attack patterns based on the classification analysis using machine learning and data mining techniques. This paper is devoted to thoroughly evaluate classifier ensembles for IDSs in IEEE 802.11 wireless network. Two ensemble techniques, i.e. voting and stacking are employed to combine the three base classifiers, i.e. decision tree (DT), random forest (RF), and support vector machine (SVM). We use area under ROC curve (AUC) value as a performance metric. Finally, we conduct two statistical significance tests to evaluate the performance differences among classifiers. © 2017 KIPS.

引用

页码：1203 / 1212