Evaluation of N-gram Based Multi-layer Approach to Detect Malware in Android

Abstract

N-gram techniques usually used in Natural Language Processing (NLP). Those techniques along with stacked generalization has been experimented and assessed in the field of android malware detection. Beacuse of the rapidly growing of android users, android malware has become most popular among the attackers. Android malware has become gigantic topics in information security. Various security researchers have already started to propose intelligency based android malware detection. In this paper, a details investigation has been performed to evaluate the effectiveness of unigram, bigram and trigram with stacked generalization. It’s been found that with stacking, unigram provides more than 97% of accuracy which is highest detection rate against bigram and trigram. In level 1, Extra Tree (ET), Random Forest (RF) and Gradient Boosting (GB) are used. As a final predictor and meta estimator eXtreme Gradient Boosting (XGBoost) is used. A strong basement to use n-gram techniques in developing android malware detection has been determined from this study.