Android Malware Detection in IoT Mobile Devices using a Meta-ensemble Classifier

Android malware is considered to be an issue that prevents wide implementation of Internet of Things. Malware detection for Android devices follow different methodologies. One of the most common due to its efficacy is static feature analysis using machine learning techniques. This paper applies a set of machine learning classification models and a soft voting meta ensemble to an open online dataset called Drebin. Our study reveals that the random forests outperformed all other classifiers, while the meta enseble classifier that utilizes the soft voting technique of the three top performing classifiers further improves classification results. The proposed method also has a similar or better performance when compared to more sophisticated methods described in the literature.