Hybrid Classification Algorithm For Denial Of Service Attack Detection Using Rough Set Theory And Artificial Immune

Denial of Service (DoS) attacks is one of the security threats for computer systems and applications. It usually makes use of software bugs to crash or freeze a service or network resource or bandwidth limits by making use of a flood attack to saturate all bandwidth. Predicting a potential DOS attac...

Full description

Saved in:

Bibliographic Details
Main Author:	Fatin Norsyafawati, Mohd Sabri
Format:	Thesis
Language:	English
Subjects:	Hybrid Systems
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-usim-ddms-12296
record_format	uketd_dc
spelling	my-usim-ddms-122962024-05-29T04:00:20Z Hybrid Classification Algorithm For Denial Of Service Attack Detection Using Rough Set Theory And Artificial Immune Fatin Norsyafawati, Mohd Sabri Denial of Service (DoS) attacks is one of the security threats for computer systems and applications. It usually makes use of software bugs to crash or freeze a service or network resource or bandwidth limits by making use of a flood attack to saturate all bandwidth. Predicting a potential DOS attacks would be very helpful for an IT departments or managements to optimize the security of intrusion detection system (IDS). Nowdays, false alarm rates and accuracy become the main subject to be addressed in measuring the effectiveness of IDS. Thus, the purpose of this work is to propose a classifier that is capable of reducing the false alarm rates and increase the accuracy of the detection system. This study applied Artifical Immune System (AIS) in IDS by introducing an improved AIS in IDS by integrating rough set theory (RST) with Artifical Immune Recognition System 1 (AIRS) algorithm (Rough-AIRS1) to categorize the DoS samples. RST is expected to be able to reduce the redundant features from huge amount of data that is capable to increase the performance of the classification. Furthermore, AIS is an incremental learning approach that will minimize duplications of cases in a knowledge based. It will be efficient in terms of memory storage and speed in searching for similarities in Intrusion Detection (IDS) attacks patterns. This study uses NSL-KDD 20% train dataset to test the classifiers. Then, the performances were compared with single AIRS1 and J48 algorithm. Results from these experiments showed that Rough-AIRS1 has lower number of false alarm rate compared to single AIRS but a little bit higher than J48. However, accuracy for this hybrid technique is lower compared to others due to higher memory cell replacement. Universiti Sains Islam Malaysia 2012-05 Thesis en https://oarep.usim.edu.my/handle/123456789/12296 https://oarep.usim.edu.my/bitstreams/8d787780-d102-4440-a8de-d2e6a520c5ad/download 8a4605be74aa9ea9d79846c1fba20a33 Hybrid Systems
institution	Universiti Sains Islam Malaysia
collection	USIM Institutional Repository
language	English
topic	Hybrid Systems
spellingShingle	Hybrid Systems Fatin Norsyafawati, Mohd Sabri Hybrid Classification Algorithm For Denial Of Service Attack Detection Using Rough Set Theory And Artificial Immune
description	Denial of Service (DoS) attacks is one of the security threats for computer systems and applications. It usually makes use of software bugs to crash or freeze a service or network resource or bandwidth limits by making use of a flood attack to saturate all bandwidth. Predicting a potential DOS attacks would be very helpful for an IT departments or managements to optimize the security of intrusion detection system (IDS). Nowdays, false alarm rates and accuracy become the main subject to be addressed in measuring the effectiveness of IDS. Thus, the purpose of this work is to propose a classifier that is capable of reducing the false alarm rates and increase the accuracy of the detection system. This study applied Artifical Immune System (AIS) in IDS by introducing an improved AIS in IDS by integrating rough set theory (RST) with Artifical Immune Recognition System 1 (AIRS) algorithm (Rough-AIRS1) to categorize the DoS samples. RST is expected to be able to reduce the redundant features from huge amount of data that is capable to increase the performance of the classification. Furthermore, AIS is an incremental learning approach that will minimize duplications of cases in a knowledge based. It will be efficient in terms of memory storage and speed in searching for similarities in Intrusion Detection (IDS) attacks patterns. This study uses NSL-KDD 20% train dataset to test the classifiers. Then, the performances were compared with single AIRS1 and J48 algorithm. Results from these experiments showed that Rough-AIRS1 has lower number of false alarm rate compared to single AIRS but a little bit higher than J48. However, accuracy for this hybrid technique is lower compared to others due to higher memory cell replacement.
format	Thesis
author	Fatin Norsyafawati, Mohd Sabri
author_facet	Fatin Norsyafawati, Mohd Sabri
author_sort	Fatin Norsyafawati, Mohd Sabri
title	Hybrid Classification Algorithm For Denial Of Service Attack Detection Using Rough Set Theory And Artificial Immune
title_short	Hybrid Classification Algorithm For Denial Of Service Attack Detection Using Rough Set Theory And Artificial Immune
title_full	Hybrid Classification Algorithm For Denial Of Service Attack Detection Using Rough Set Theory And Artificial Immune
title_fullStr	Hybrid Classification Algorithm For Denial Of Service Attack Detection Using Rough Set Theory And Artificial Immune
title_full_unstemmed	Hybrid Classification Algorithm For Denial Of Service Attack Detection Using Rough Set Theory And Artificial Immune
title_sort	hybrid classification algorithm for denial of service attack detection using rough set theory and artificial immune
granting_institution	Universiti Sains Islam Malaysia
_version_	1812444683913134080

Hybrid Classification Algorithm For Denial Of Service Attack Detection Using Rough Set Theory And Artificial Immune

Similar Items