作者: Suleiman Y. Yerima , Sakir Sezer , Igor Muttik
关键词:
摘要: The battle to mitigate Android malware has become more critical with the emergence of new strains incorporating increasingly sophisticated evasion techniques, in turn necessitating advanced detection capabilities. Hence, this paper we propose and evaluate a machine learning based approach on eigenspace analysis for using features derived from static characterization applications. Empirical evaluation dataset real benign samples show that rate over 96% very low false positive is achievable proposed method.