Normal view MARC view ISBD view

Network instrusion prevention system ( NIPS) based on network intrusion detection system (NIDS) and ID3 algorithm decision tree classifier / Syurahbil

By:

Syurahbil

Material type: Text

TextPublication details: Kuantan, Pahang : UMP, 2011Description: xix, 142 p . : ill. ; 30 cm. + 1 CD-ROMISBN:

THE0003667(Local)

Subject(s):

Dissertation note: Thesis (Master of Science (Computer)) -- Universiti Malaysia Pahang - 2011 Abstract: Network security has gained significant attention in research and industrial communities. Due to the increasing threat of the network intrusion, firewalls have become important elements of the security policy. Firewall performance highly depends toward number of rules, because the large more rules the consequence makes downhill performance progressively. Firewall can be allow or deny access network packets incoming and outgoing into Local Area Network (LAN), but firewall can not detect intrusion. To distinguishing an intrusion network packet or normal is very difficult and takes a lot of time. An analyst must review all the network traffics previously. In this study, a new way to make the rules that can determine network packet is intrusion or normal automatically. These rules implemented into firewall as prevention, which if there is a network packet that match these rules then network packet will be dropped. This is called Network Intrusion Prevention System(NIPS).These rules are generated based on Network Intrusion Detection System (NIDS) and Iterative Dichotomiser 3 (ID3) Algorithm Decision Tree Classifier, which as data training is intrusion network packet and normal network packets from previous network traffics. The experiment is successful, which can generate the rules then implemented into a firewall and drop the intrusion network packet automatically. Moreover, this way can minimize number of rules in firewall.

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings ( 2 )
Title notes ( 3 )

Holdings
Item type	Current library	Call number	Copy number	Status	Date due	Barcode
Thesis	UMPLIB GAMBANG	CD 6002 \| TK5105.59 .S98 2011 rs Thesis (Browse shelf(Opens below))	1	Not for loan		0000063479
Thesis	UMPLIB PEKAN	TK5105.59 .S98 2011 rs Thesis (Browse shelf(Opens below))	1	Not for loan		0000063478

Thesis (Master of Science (Computer)) -- Universiti Malaysia Pahang - 2011

Bibliography : p. 97-101

Network security has gained significant attention in research and industrial communities. Due to the increasing threat of the network intrusion, firewalls have become important elements of the security policy. Firewall performance highly depends toward number of rules, because the large more rules the consequence makes downhill performance progressively. Firewall can be allow or deny access network packets incoming and outgoing into Local Area Network (LAN), but firewall can not detect intrusion. To distinguishing an intrusion network packet or normal is very difficult and takes a lot of time. An analyst must review all the network traffics previously. In this study, a new way to make the rules that can determine network packet is intrusion or normal automatically. These rules implemented into firewall as prevention, which if there is a network packet that match these rules then network packet will be dropped. This is called Network Intrusion Prevention System(NIPS).These rules are generated based on Network Intrusion Detection System (NIDS) and Iterative Dichotomiser 3 (ID3) Algorithm Decision Tree Classifier, which as data training is intrusion network packet and normal network packets from previous network traffics. The experiment is successful, which can generate the rules then implemented into a firewall and drop the intrusion network packet automatically. Moreover, this way can minimize number of rules in firewall.