Advancing Android Malware Detection with Machine Learning Techniques

Mathew, Jospeh (2024) Advancing Android Malware Detection with Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (744kB) | Preview
Preview	PDF (Configuration Manual) Download (482kB) | Preview

Abstract

Malware incidents are on the rise and are a great danger for information security. This project describes the application of a Random Forest technique for classifying applications into two groups: benign and malware. The model's real time predictive ability is further evaluated towards that end, and its ability in a cybersecurity context may prove valuable. The experiments show that Random Forest classifier can make effective malware detection, class distinction and accurate predictions. To this end, the real time predictive ability of the model is evaluated that may be helpful in a cybersecurity context. All the experiments reveal that Random Forest classifier has the possibility to be implemented for the detection of malware and can differentiate between the classes and make better predictions. More research may include improving the model to improve the hyperparameters, features selection, and managing class imbalance to enhance the performance of the model.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Khan, Imran 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 > 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:	17 Jul 2025 14:27
Last Modified:	17 Jul 2025 14:27
URI:	https://norma.ncirl.ie/id/eprint/8169

Actions (login required)

View Item