System malware detection in the type of operating system ANDROID

Abstract

As part of this work has been tasked to improve the efficiency of detection of malicious software in the operating system for mobile devices such as Android. To achieve this goal the analysis of security of the Android operating system and the formalization of malware samples in order to identify features inherent in their behavior. Based on the information developed an experimental sample consisting of the vectors describing the behavioral nature of the two types of programs: safe - ok and malware - virus. As a result of research experiments chosen classification method which performs classification proposed sample with the highest accuracy. The problem is increasing the efficiency of detection of malicious software is solved with the use of the developed method based on support vector machines and apparatus of fuzzy logic. This method is implemented in the form of studies of the prototype malware detection system.