NORMA eResearch @NCI Library

Optimizing Network Security: Performance Analysis of Neural Network Models for Intrusion Detection

Saravanan, Ranjith Kumar (2024) Optimizing Network Security: Performance Analysis of Neural Network Models for Intrusion Detection. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (730kB) | Preview

Abstract

Since cybersecurity threats became more intelligent, defending against them required high-powered mechanisms to maintain network integrity. As such, the report devised potent intrusion detection models using the NSL-KDD dataset. The dataset included various vital threats and hazards, such as the back, neptune, portsweep, and smurf alongside normal traffic. The effectiveness of the Artificial Neural Networks and Long Short-Term Memory LSTM models was tested on these samples. The results demonstrated a validation accuracy of 66.70% for the ANN and 99.10% for the LSTM, offering a novel neural network approach to these major types of malicious shellcode, rather than depending on previous signature-based methods. The developed approach enabled outstanding accuracy and far fewer false positives than before, providing an improvement in cybersecurity.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Hafeez, Khadija
UNSPECIFIED
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
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Ciara O'Brien
Date Deposited: 31 Jul 2025 08:36
Last Modified: 31 Jul 2025 08:36
URI: https://norma.ncirl.ie/id/eprint/8365

Actions (login required)

View Item View Item