NORMA eResearch @NCI Library

Improve the detection accuracy and performance of intrusion detection system using deep Bi-Directional LSTM

Sheikh, Saifullah (2021) Improve the detection accuracy and performance of intrusion detection system using deep Bi-Directional LSTM. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (835kB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (955kB) | Preview

Abstract

Intrusion detection systems are used to monitor the network for anomalies to prevent hostile attacks on the entire network. Many firms are now having NIDS problems, which causes large quantities of false alerts when hostile activities are found and IDS raises their alarm, however, we remain mystified because the complicated environment is not especially flexible. The IDS performance was slower or dropped by considerable amounts of false alarms, which makes this sensitive duty difficult, and the management of overall network intrusion detection is costlier due to the large computational effort. The same and key properties of the entire network and computer security have been studied extensively. Intrusion classification into UNSW-NB15 by classifying network difficulties by updating and installing new, efficient technologies that may be readily categorized into a UNSW-NB15 dataset intrusion identifier. A new Deep Bi-directional LSTM strategy will be proposed to build an updated detection model to minimize or accuracy of the false alarm rate.

Item Type: Thesis (Masters)
Uncontrolled Keywords: IDS; Deep Bi-directional LSTM; Neural Networking; Cyberspace Security
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software > Computer Security
T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Clara Chan
Date Deposited: 02 Nov 2021 10:07
Last Modified: 02 Nov 2021 10:07
URI: https://norma.ncirl.ie/id/eprint/5127

Actions (login required)

View Item View Item