Advancing Malware Detection: A Deep Learning Approach with Transfer Learning Techniques

George, Little Tresa (2024) Advancing Malware Detection: A Deep Learning Approach with Transfer Learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (852kB) | Preview

Abstract

In the progressing cyber world, malware creates a notable threat to data security, underscoring the need for timely detection to mitigate its impact. Traditional detection systems, such as signature-based methods, are becoming successful against highly complicated attacks. This paper offers deep learning approaches to malware detection, focusing on comparing the performance of advanced convolutional neural network (CNN) architectures such as XceptionNet, EfficientNetB0, and ResNet50. By examining various patterns from the image data, the system predicts the presence of malware. The models show better accuracy compared to traditional methods. It successfully diminishes the likelihood of misclassification, thus improving the precision of detection. The proposed system's accuracy in detecting malware assists the cyber security department, enabling better cyber-threat handling. EfficientNetB0 emerges as the most accurate model, achieving 96% accuracy, outperforming both XceptionNet and ResNet50, which recorded 95% accuracy. Overall, the research paper aims to present how well these deep learning models can detect the presence of malware by identifying known and unknown malware strains and considering challenges such as disproportionate datasets, adversarial attacks, and the need for real-time detection in cybersecurity employment.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hafeez, Khadija UNSPECIFIED
Uncontrolled Keywords:	Xception; EfficientNetB0; ResNet
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:	23 Jul 2025 13:26
Last Modified:	23 Jul 2025 13:26
URI:	https://norma.ncirl.ie/id/eprint/8209

Actions (login required)

View Item