Mobile Malware Detection in the Real World

Several works in literature address the mobile malware detection problem by classifying features obtained from real world application and using well-known machine-learning techniques. Several authors have published empirical studies aimed at assessing the quality of set of features. In this paper we propose BehaveYourself!, an Android application able to discriminate a trusted application by a malicious one extracting opcode-based features. Our application is open and flexible: it can be used as a starting point to define, and experiment with, additional features. We release BehaveYourself! to the research community at the following url: http://www.ing.unisannio.it/cimitile/BehaveYourself.apk.