Application of Machine Learning Algorithms for Android Malware Detection

摘要: As the popularity of Android smart devises increases, battle alleviating malware has been considered as a crucial activity with advent new attacks including progressively complicated evasion techniques, consequently entailing more cutting-edge detection techniques. Hence, in this paper, two Machine Learning (ML) algorithms, called Support Vector (SVM) and K-Nearest Neighbors (KNN), are applied evaluated to perform classification feature set into either benign or malicious applications (apps) through supervised learning process. This work involves static analysis apps, which checks for presence frequency keywords apps' manifest file derives sets from 400-app dataset produce better results. The performance ML algorithms is measured terms accuracy true positive rate interpreted determine algorithm applicable detection. experimental results real apps indicate average 79.08% 80.50% over 67.00% 80.00% using SVM KNN, respectively.