A Comparative Analysis of Kernel-Based Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) for zero-day Malware Detection

Shanmugam, Annamalai (2023) A Comparative Analysis of Kernel-Based Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) for zero-day Malware Detection. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (7MB) | Preview
Preview	PDF (Configuration Manual) Download (10MB) | Preview

Abstract

This study conducts a comparative analysis of Support Vector Machines (SVM) and 1D Convolutional Neural Networks (CNN) for the detection of zero-day malware, a critical issue in cybersecurity due to the absence of known signatures for such advanced threats. The research is driven by the necessity for models that excel in predicting and generalizing to new, unseen malware samples. A dataset representing a realistic spectrum of malware was used to train and evaluate the performance of both algorithms. The findings highlight that: the CNN 1D model achieved a perfect accuracy rate of 100% in identifying zero-day threats, while the SVM model also performed exceptionally well with an accuracy of 99%. The superior performance of the CNN 1D is attributed to its ability to learn temporal features from sequential data, which is pivotal in recognizing the sophisticated patterns of zero-day malware. These results highlight the effectiveness of CNN 1D models in malware detection, suggesting their suitability for deployment in advanced cybersecurity systems. The research concludes that the adaptability and precision of CNN 1D make it a potentially valuable tool in combating the ever-changing landscape of cyber threats.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jayasekera, Evgeniia 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 > Algebra > Algorithms > Computer algorithms 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:	25 Apr 2025 08:14
Last Modified:	25 Apr 2025 08:14
URI:	https://norma.ncirl.ie/id/eprint/7464

Actions (login required)

View Item