A Study Of Machine Learning Classifiers for Anomaly-Based Mobile Botnet Detection

Malaysian Journal of Computer Science

Shahaboddin Shamshirband¹  Rosli Salleh¹  Ra’uf Ridzuan Ma’arof¹  Nor Badrul Anuar¹  Ali Feizollah¹  Fairuz Amalina¹ 

关键词: Mobile botnet;    machine learning classifiers;    anomaly-based detection;    intrusion detection systems;   

DOI  :  

学科分类：社会科学、人文和艺术（综合）

来源: University of Malaya * Faculty of Computer Science and Information Technology

【 摘 要 】

In recent years, mobile devices are ubiquitous. They are employed for purposes beyond merely making phonecalls. Among the mobile operating systems, Android is the most popular due to its availability as an open sourceoperating system. Due to the proliferation of Android malwares, it is crucial to study the best classifiers that candetect these malwares effectively and accurately through selecting the most suitable network traffic features aswell as comprehensive comparison with related works. This study evaluates five machine learning classifiers,namely Naïve Bayes, k-nearest neighbour, decision tree, multi-layer perceptron, and support vector machine.The evaluation was validated using malware data samples from the Android Malware Genome Project. Thedata sample is a collection of malwares gathered between August 2010 and October 2011 by the University ofNorth Carolina. Among various network traffic characteristics, three network features were selected:connection duration, TCP size and number of GET/POST parameters. From the experiment, it is found that knearestneighbour provides the optimum results in terms of performance among the classifiers. Theexperimental results also indicate a true positive rate as high as 99.94% and false positive of 0.06% for the knearestneighbour classifier.

【 授权许可】

Unknown