A New Approach to Improve Mobile Network’s Security Through Android Malware Detection Utilizing StaticAnalysis

The security of the mobile devices has become a major issue since hackers target them throughmalwares in order to harm the systems or gather sensitive information and get access to the systemsremotely. Recently, new ways have been introduced to confront malwares and other viruses. Twomain techniques for recognizing malwares are dynamic analysis and static analysis. This paperproposes a new method using the static analysis to help improve the accuracy of the malwares indetecting threats faster and with lower processing time. For this purpose, our suggested method hasutilized the android application’s main components to recognize the malwares using the machinelearning algorithms. Furthermore, our method has used the feature selection algorithms to reduce theprocessing overload and to enhance the speed and accuracy. Our method have used the followingcomponents as the classification features in our suggested algorithms: API calls, Intents, networkaddress and IPs, services and provider, activities and permissions. In addition to these individualfeatures, our method has also employed complex features to improve malware recognition. We haveused 123,446 software and 5,561 malwares to evaluate the accuracy and the precision of the suggestedmethod, demonstrating to be 99.4 percent.

Keywords:

Android Security , Malware Detection , Static Analysis , Classification , Machine Learning