Investigation of Machine Learning Algorithms for Malware Detection in PE and PDF Files

Usoroh, Rosemary Uwem (2024) Investigation of Machine Learning Algorithms for Malware Detection in PE and PDF Files. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Malware is a malicious program that uses harmful operations to destroy computer systems, get financial gain and steal confidential data. Many organizations lose their data, money and reputation because of malware attack. Therefore, malware detection is a crucial task in the cyber security field. Due to the dynamic nature of malware and the presence of new variants, the digital world must be protected from malware threats by the detection of malware using machine learning algorithms. Malware detection can be done in different file formats and files are the fundamental tools used to run software. The motivation of this research is to detect malware accurately in Portable Executable (PE) and Portable Document Format (PDF) files. This research contributes to the body of research by investigating the use of machine learning algorithms in the detection of malware. This work combined the use of four datasets with 33, 54, 92 and 631 features. Different machine learning (ML) algorithms were used to analyze the dataset. The machine learning algorithms includes, PART rule (PART), Ordinal Class Classifier (OCC), and Bayes Network (BN). The machine learning models were built and evaluated, the results from the experiments showed that OCC and PART models were the best classifiers with 100% accuracy on the WinMal dataset with 631 features. This research can be used for future work in malware detection and mitigation.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Moldovan, Arghir-Nicolae 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:	26 Apr 2025 10:11
Last Modified:	26 Apr 2025 10:11
URI:	https://norma.ncirl.ie/id/eprint/7477

Actions (login required)

View Item