Deep learning for detecting Android malwares

Abstract

The revolution and development of malwares over time necessitate an intensive researches on advanced techniques to secure user's personal and critical information, the most challenging task is to build a strong and robust classifier allows to detect different types of malwares and being able to defeat zero-day malware attacks. Machine learning algorithms as SVM (support vector machine), Random Forest and Naive Bayes are well-known choices for building the malware classifier, even though the deep learning which is a subfield of machine learning, has a portion in classifying android malwares with high precision. In this paper we present a modest study on difference between using both techniques and proposition of an approach based on deep learning technique applied on Apk of android applications belong to a heterogeneous data combined of benign and malware applications of different types.