Android Malware Detection Using Machine Learning

Malware, or malicious software, poses a significant threat to systems and networks. Malware attacks are becoming extremely sophisticated, and the ability to detect and prevent them is becoming more challenging. Detecting and preventing malware is crucial for several reasons, including the security of personal information, data loss and tampering, system disruptions, financial losses, and reputation damage. This paper presents a machine learning approach for Android malware detection. In this work, several machine learning algorithms were utilized, namely k-Nearest neighbor (KNN), Decision Trees (DT), Naive Bayes (NB), Support Vector Machine (SVM) and other ensemble classifiers including Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM) and CatBoost. It was found that SVM using radial basis function (RBF) kernel achieved the highest performance with an accuracy of 99.5%. This work proved the feasibility of using machine learning in detecting malware and improving the security of mobile devices. The results of this work can be used to build more robust systems to protect devices and networks from malicious attacks.