With the increase of network components connected to the Internet, the need to ensure secure connectivity is becoming increasingly vital. Intrusion Detection Systems (IDSs) are one of the common security components that identify security violations. This paper proposes a novel multilevel hybrid classifier that uses different feature sets on each classifier. It presents the Discernibility Function based Feature Selection method and two classifiers involving multilayer perceptron (MLP) and decision tree (C4.5). Experiments are conducted on the KDD'99 Cup and ISCX datasets, and the proposal demonstrates better performance than individual classifiers and other proposed hybrid classifiers. The proposed method provides significant improvement in the detection rates of attack classes and Cost Per Example (CPE) which was the primary evaluation method in the KDD'99 Cup competition.
Aslhan AKYOL
Mevlana University
Mehmet HACIBEYOĞLU
Necmettin Erbakan University
Bekir KARLIK
Beykent University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Aslhan AKYOL, Mehmet HACIBEYOĞLU, Bekir KARLIK, "Design of Multilevel Hybrid Classifier with Variant Feature Sets for Intrusion Detection System" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 7, pp. 1810-1821, July 2016, doi: 10.1587/transinf.2015EDP7357.
Abstract: With the increase of network components connected to the Internet, the need to ensure secure connectivity is becoming increasingly vital. Intrusion Detection Systems (IDSs) are one of the common security components that identify security violations. This paper proposes a novel multilevel hybrid classifier that uses different feature sets on each classifier. It presents the Discernibility Function based Feature Selection method and two classifiers involving multilayer perceptron (MLP) and decision tree (C4.5). Experiments are conducted on the KDD'99 Cup and ISCX datasets, and the proposal demonstrates better performance than individual classifiers and other proposed hybrid classifiers. The proposed method provides significant improvement in the detection rates of attack classes and Cost Per Example (CPE) which was the primary evaluation method in the KDD'99 Cup competition.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7357/_p
Copy
@ARTICLE{e99-d_7_1810,
author={Aslhan AKYOL, Mehmet HACIBEYOĞLU, Bekir KARLIK, },
journal={IEICE TRANSACTIONS on Information},
title={Design of Multilevel Hybrid Classifier with Variant Feature Sets for Intrusion Detection System},
year={2016},
volume={E99-D},
number={7},
pages={1810-1821},
abstract={With the increase of network components connected to the Internet, the need to ensure secure connectivity is becoming increasingly vital. Intrusion Detection Systems (IDSs) are one of the common security components that identify security violations. This paper proposes a novel multilevel hybrid classifier that uses different feature sets on each classifier. It presents the Discernibility Function based Feature Selection method and two classifiers involving multilayer perceptron (MLP) and decision tree (C4.5). Experiments are conducted on the KDD'99 Cup and ISCX datasets, and the proposal demonstrates better performance than individual classifiers and other proposed hybrid classifiers. The proposed method provides significant improvement in the detection rates of attack classes and Cost Per Example (CPE) which was the primary evaluation method in the KDD'99 Cup competition.},
keywords={},
doi={10.1587/transinf.2015EDP7357},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Design of Multilevel Hybrid Classifier with Variant Feature Sets for Intrusion Detection System
T2 - IEICE TRANSACTIONS on Information
SP - 1810
EP - 1821
AU - Aslhan AKYOL
AU - Mehmet HACIBEYOĞLU
AU - Bekir KARLIK
PY - 2016
DO - 10.1587/transinf.2015EDP7357
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2016
AB - With the increase of network components connected to the Internet, the need to ensure secure connectivity is becoming increasingly vital. Intrusion Detection Systems (IDSs) are one of the common security components that identify security violations. This paper proposes a novel multilevel hybrid classifier that uses different feature sets on each classifier. It presents the Discernibility Function based Feature Selection method and two classifiers involving multilayer perceptron (MLP) and decision tree (C4.5). Experiments are conducted on the KDD'99 Cup and ISCX datasets, and the proposal demonstrates better performance than individual classifiers and other proposed hybrid classifiers. The proposed method provides significant improvement in the detection rates of attack classes and Cost Per Example (CPE) which was the primary evaluation method in the KDD'99 Cup competition.
ER -