Malware detection method of android application based on simplification instructions

Abstract

The amount of mobile malicious code is increasing faster every year and a serious security threat is posed by this. Hence, malware detection has become a critical topic in the field of computer security. This paper proposes a method to detect variants of known malware families in Android devices using simplify Dalvik instructions. This method is based on the sequence of instructions. A method is described in this paper to give the simplified description of each instruction and group them with n-gram patterns, which are set to be the malicious features. The result of the experiment shows that features extracted by this method are easy to be recognized, thus an effective way to detect variants of known malware families is provided. © 2014 The Journal of China Universities of Posts and Telecommunications.