Metaheuristic-Based Neural Network Training And Feature Selector For Intrusion Detection

Intrusion Detection (ID) in the context of computer networks is an essential technique in modern defense-in-depth security strategies. As such, Intrusion Detection Systems (IDSs) have received tremendous attention from security researchers and professionals. An important concept in ID is anomaly det...

Full description

Saved in:

Bibliographic Details
Main Author:	Ghanem, Waheed Ali Hussein Mohammed
Format:	Thesis
Language:	English
Published:	2019
Subjects:	QA75.5-76.95 Electronic computers Computer science
Online Access:	http://eprints.usm.my/46632/1/WaheedGhanem-Phd201924.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-usm-ep.46632
record_format	uketd_dc
spelling	my-usm-ep.466322020-06-26T08:38:56Z Metaheuristic-Based Neural Network Training And Feature Selector For Intrusion Detection 2019-04 Ghanem, Waheed Ali Hussein Mohammed QA75.5-76.95 Electronic computers. Computer science Intrusion Detection (ID) in the context of computer networks is an essential technique in modern defense-in-depth security strategies. As such, Intrusion Detection Systems (IDSs) have received tremendous attention from security researchers and professionals. An important concept in ID is anomaly detection, which amounts to the isolation of normal behavior of network traffic from abnormal (anomaly) events. This isolation is essentially a classification task, which led researchers to attempt the application of well-known classifiers from the area of machine learning to intrusion detection. Neural Networks (NNs) are one of the most popular techniques to perform non-linear classification, and have been extensively used in the literature to perform intrusion detection. However, the training datasets usually compose feature sets of irrelevant or redundant information, which impacts the performance of classification, and traditional learning algorithms such as backpropagation suffer from known issues, including slow convergence and the trap of local minimum. Those problems lend themselves to the realm of optimization. Considering the wide success of swarm intelligence methods in optimization problems, the main objective of this thesis is to contribute to the improvement of intrusion detection technology through the application of swarm-based optimization techniques to the basic problems of selecting optimal packet features, and optimal training of neural networks on classifying those features into normal and attack instances. To realize these objectives, the research in this thesis follows three basic stages, succeeded by extensive evaluations. 2019-04 Thesis http://eprints.usm.my/46632/ http://eprints.usm.my/46632/1/WaheedGhanem-Phd201924.pdf application/pdf en public phd doctoral Universiti Sains Malaysia Pusat Pengajian Sains Komputer
institution	Universiti Sains Malaysia
collection	USM Institutional Repository
language	English
topic	QA75.5-76.95 Electronic computers Computer science
spellingShingle	QA75.5-76.95 Electronic computers Computer science Ghanem, Waheed Ali Hussein Mohammed Metaheuristic-Based Neural Network Training And Feature Selector For Intrusion Detection
description	Intrusion Detection (ID) in the context of computer networks is an essential technique in modern defense-in-depth security strategies. As such, Intrusion Detection Systems (IDSs) have received tremendous attention from security researchers and professionals. An important concept in ID is anomaly detection, which amounts to the isolation of normal behavior of network traffic from abnormal (anomaly) events. This isolation is essentially a classification task, which led researchers to attempt the application of well-known classifiers from the area of machine learning to intrusion detection. Neural Networks (NNs) are one of the most popular techniques to perform non-linear classification, and have been extensively used in the literature to perform intrusion detection. However, the training datasets usually compose feature sets of irrelevant or redundant information, which impacts the performance of classification, and traditional learning algorithms such as backpropagation suffer from known issues, including slow convergence and the trap of local minimum. Those problems lend themselves to the realm of optimization. Considering the wide success of swarm intelligence methods in optimization problems, the main objective of this thesis is to contribute to the improvement of intrusion detection technology through the application of swarm-based optimization techniques to the basic problems of selecting optimal packet features, and optimal training of neural networks on classifying those features into normal and attack instances. To realize these objectives, the research in this thesis follows three basic stages, succeeded by extensive evaluations.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Ghanem, Waheed Ali Hussein Mohammed
author_facet	Ghanem, Waheed Ali Hussein Mohammed
author_sort	Ghanem, Waheed Ali Hussein Mohammed
title	Metaheuristic-Based Neural Network Training And Feature Selector For Intrusion Detection
title_short	Metaheuristic-Based Neural Network Training And Feature Selector For Intrusion Detection
title_full	Metaheuristic-Based Neural Network Training And Feature Selector For Intrusion Detection
title_fullStr	Metaheuristic-Based Neural Network Training And Feature Selector For Intrusion Detection
title_full_unstemmed	Metaheuristic-Based Neural Network Training And Feature Selector For Intrusion Detection
title_sort	metaheuristic-based neural network training and feature selector for intrusion detection
granting_institution	Universiti Sains Malaysia
granting_department	Pusat Pengajian Sains Komputer
publishDate	2019
url	http://eprints.usm.my/46632/1/WaheedGhanem-Phd201924.pdf
_version_	1747821701102567424

Metaheuristic-Based Neural Network Training And Feature Selector For Intrusion Detection

Similar Items