Enhancing Malware Detection and Classification Using Deep Learning: A High Accuracy and Low Latency Approach

Mmesirionye, Ahaoma Emmanuel (2025) Enhancing Malware Detection and Classification Using Deep Learning: A High Accuracy and Low Latency Approach. Masters thesis, Dublin, National College of Ireland.

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

Abstract

The study of malware and its detection and classification has become a very important aspect of cybersecurity, as it enables the identification and classification of several variants of malware in network operations. In this study, the proposition of a comparative analysis between four (4) deep learning techniques for the enhancement of this malware detection was carried out on a dataset obtained from Kaggle, the Windows malware that comprises the SOMLAP dataset. The four (4) deep learning algorithms proposed in this research include multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM), and recurrent neural network (RNN). After the training and evaluation of the models, the long short-term memory (LSTM) was observed as the most efficient model for the detection of malware after achieving an accuracy of 97%. One of the few limitations encountered in this research is due to the constant evolution of malware, and while these deep learning neural network algorithms can detect patterns in the malware structure, they may require frequent retraining to adapt to newly emerging malware threats. However, the results obtained from the research underscore the potential of deep learning sequential models in the enhancement of malware detection. This research contributes to the growing field of cybersecurity, as it offers insights into the advantages of employing deep learning technologies in the quest to mitigate malicious software vulnerabilities in our industry.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Monaghan, Mark UNSPECIFIED
Uncontrolled Keywords:	Malware; multilayer perceptron; convolutional neural network; long short-term memory; recurrent neural network; accuracy; cybersecurity
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:	15 Jun 2026 14:53
Last Modified:	15 Jun 2026 14:53
URI:	https://norma.ncirl.ie/id/eprint/9361

Actions (login required)

View Item