Malware Detection Using Machine Learning Algorithms and Reverse Engineering of Android Java Code

Abstract

This research paper is focused on the issue of mobile application malware detection by Reverse Engineering of Android java code and use of Machine Learning algorithms. The malicious software characteristics were identified based on a collected set of total number of 1958 applications (including 996 malware applications). During research a unique set of features was chosen, then three attribute selection algorithms and five classification algorithms (Random Forest, K Nearest Neighbors, SVM, Nave Bayes and Logistic Regression) were examined to choose algorithms that would provide the most effective rate of malware detection.

K-Nearest Neighbour Classifier Usage for Permission Based Malware Detection in Android

“…On average, 92.63% correct classication rate was catched. In the study prepared by Kedziora et al [30], tests were carried out with a total of 1958 application including 996 malicious software. In the classification modeled with KNN, performance values varying between 78.3% and 80% were obtained for different metrics.…”