In today's digital landscape, the rise of malware poses a significant threat to the security and integrity of computer systems and networks. Traditional signature-based detection methods are increasingly inadequate against the evolving nature of sophisticated malware variants. Therefore, there is an urgent need for innovative malware detection approaches that can adapt to emerging threats in real-time. This research aims to develop a malware detection system utilizing machine learning algorithms. Specifically, the Random Forest classifier and Logistic Regression were employed for the classification of malware based on features extracted from the CIC-MalMem-2022 dataset. The malware detection system model was implemented using the Python programming language and evaluated using four key performance metrics: F1-score, precision, recall, and accuracy. A comparison between the logistic regression model and the random forest model revealed that the Random Forest approach outperformed the logistic model in malware detection, achieving an accuracy of 98% compared to 94%.

Authors: Otasowie Owolafe, Ilobekemen P. Oladoja, Ayomide S. Olajide

Published in: International Conference for Internet Technology and Secured Transactions (ICITST-2024)

• Date of Conference: 4-6 November 2024
• DOI: 10.20533/ICITST.2024.0014
• ISBN: 978-1-913572-76-1
• Conference Location: St Anne’s College, Oxford University, UK