Machine learning aided android malware classification

The widespread adoption of Android devices and their capability to store access significant private and confidential information have resulted in these devices being targeted by malware developers. Existing Android malware analysistechniques can be broadly categorized into static and dynamic analysis. Inthis paper, we present two machine learning aided approaches for static analysis of Android malware. The first approach is based on permissions and theother is based on source code analysis utilizing a bag-of-words representationmodel. Our permission-based model is computationally inexpensive, and is implemented as the OWASP Seraphimdroid Android app that can be obtainedfrom Google Play Store. Our evaluations of both approaches indicate an F-score of 95.1% and F-measure of 89% for the source code-based classificationand permission-based classification models, respectively