Comparative Analysis of Random Forest and Support Vector Machine Classifiers for unjustified malware detection of Android Devices Data Consuming SMOTE and ROC-AUC Metrices

The production of Android devices has led to a significant rise in malware targeting this platform, posing large security risks. This study conducts a comparative analysis of two prominent machine learning classifiers, Random Forest (RF) and Support Vector Machine (SVM), for detecting unjustified malware in Android devices. Given the characteristic imbalance in malware detection datasets, we employed the Synthetic Minority Over-sampling Technique (SMOTE) to improve the minority class representation, confirming a robust assessment of classifier performance. The classifiers efficiency was measured using the Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) metrics. Our findings specify that both RF and SVM display high accuracy in characteristic between benign and malicious applications, with RF demonstrating a small edge in terms of AUC score. This research underscores the importance of addressing data imbalance and provides insights into the applicability of RF and SVM in malware detection. Future work could explore the integration of additional features and the use of deep learning techniques to more enhance detection abilities.