Improving the precision of network intrusion detection in edge computing by incorporating optimizers with Bi-directional LSTM

Arora, Vaishali (2023) Improving the precision of network intrusion detection in edge computing by incorporating optimizers with Bi-directional LSTM. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The rapid evolution of technology has propelled a surge in network intrusions, necessitating robust intrusion detection systems in edge computing. This study explores multiple Deep Learning models for network intrusion detection in edge computing including Long Short-Term Memory (LSTM), Bi-directional Long Short-Term Memory (Bi-LSTM), and Bi-directional Long Short-Term Memory with Particle Swarm Optimization (BILSTM with PSO) were implemented and evaluated to determine their effectiveness in discerning intrusion patterns within network traffic. The dataset used, UNSW-NB15, comprises diverse cyber-attack scenarios, making it a suitable benchmark cloud for testing intrusion detection models of the cloud. The models were rigorously tested using accuracy, macro-average precision, recall, and F1 scores. The results show that performance improved significantly as models progressed from LSTM (accuracy: 91%) to BILSTM (accuracy: 95%), with the apex being BILSTM with PSO, which achieved an exceptional accuracy of 99 percent while also demonstrating superior macro-average precision, recall, and F1-score. Furthermore, a qualitative analysis highlights the presented models’ practical consequences, scalability, limits, and future possibilities. This study’s findings highlight the BILSTM model’s tremendous potential for robustly recognizing network intrusions in edge computing, providing insights for improving cybersecurity techniques in a variety of network contexts of the cloud.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Makki, Ahmed UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing 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 Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	25 Mar 2025 17:54
Last Modified:	25 Mar 2025 17:54
URI:	https://norma.ncirl.ie/id/eprint/7328

Actions (login required)

View Item