Android Mobile Malware Detection Using Machine Learning

This paper presents a comprehensive comparative analysis of Random Forest (RF), Support Vector Machine (SVM), and Naive Bayes (NB) classifiers for Android malware detection using static feature analysis. Our approach achieves 98.7% accuracy with Random Forest, outperforming SVM (98.5%) while establishing Decision Tree and RF as transparent baselines for future research. The study contributes to the field by demonstrating the effectiveness of static feature based machine learning for detecting malicious Android applications and addresses critical limitations in data privacy for malware detection.