Malware Detection in Android Application using Static Permission

This work proposes a method for detecting Android malware by leveraging static permissions and machine learning algorithms. A dataset of 398 Android applications was compiled, with potential malware behaviour identified through analysis of Android API usage. After preprocessing the dataset, three machine learning algorithms―Naive Bayes, Decision Tree, and K-Neighbours―were trained and their accuracies compared. Naive Bayes demonstrated the highest accuracy, making it the most suitable algorithm for detecting Android malware using static permissions. The proposed method offers an effective approach to identifying potential malware behaviour in Android applications, ultimately contributing to a more secure Android ecosystem.