Android Malware Category and Family Identification Using Parallel Machine Learning
نویسندگان
1 M.Sc. in Systems and Computers Engineering, Department of Systems and Computers Engineering, Faculty of Engineering Al-Azhar University, Cairo, Egypt.
2 Professor, Department of Systems and Computers Engineering, Faculty of Engineering Al-Azhar University, Cairo, Egypt.
3 Assistant Professor, Department of Systems and Computers Engineering, Faculty of Engineering Al-Azhar University, Cairo, Egypt; Software Engineering and Information Technology, Faculty of Engineering and technology, Egyptian Chinese University, Cairo, Egypt.
doi
10.22059/jitm.2022.88133چکیده
Android malware is one of the most dangerous threats on the Internet. It has been on the rise for several years. As a result, it has impacted many applications such as healthcare, banking, transportation, government, e-commerce, etc. One of the most growing attacks is on Android systems due to its use in many devices worldwide. De-spite significant efforts in detecting and classifying Android malware, there is still a long way to improve the detection process and the classification performance. There is a necessity to provide a basic understanding of the behavior displayed by the most common Android malware categories and families. Hence, understand the distinct ob-jective of malware after identifying their family and category. This paper proposes an effective systematic and functional parallel machine-learning model for the dynamic detection of Android malware categories and families. Standard machine learning classifiers are implemented to analyze a massive malware dataset with 14 major mal-ware categories and 180 prominent malware families of the CCCS-CIC-AndMal2020 on dynamic layers to detect Android malware categories and families. The paper ex-periments with many machine learning algorithms and compares the proposed model with the most recent related work. The results indicate more than 96 % accuracy for Android Malware Category detection and more than 99% for Android Malware family detection overperforming the current related methods. The proposed model offers a highly accurate method for dynamic analysis of Android malware that cuts down the time required to analyze smartphone malware.
