Detection of malicious software using classical and neural network classification methods

Formulation of the problem: the spectrum of problems solved by modern mobile systems such as Android is constantly growing. This is because on the one hand by the potential opportunities that are implemented in hardware, as well as their integration with modern information technologies, which in turn harmoniously complement and create powerful hardware and software information systems, capable of performing many functions, including pro- information boards. Increasing the flow of information, complexity of the processes and of the hardware and software component devices such as Android, forcing developers to create new means of protection, efficiency and qualitative performing the process. This is especially important in the development of automated systems instrumental performing classification (clustering) of existing software into two classes: safe and malicious software. The aim is to increase the reliability and quality of recognition of modern built-in security of information, as well as the rationale and the selection methods of carrying out these functions. The methods used are: to accomplish the goals are analyzed and used classical methods of classification, neural network method based on standard architectures, and support vector machine (SVM - machine). Novelty: The paper presents the concept of the use of support vector in identifying deleterious software developed methodological, algorithmic and software that implements this concept in relation to the means of mobile communication. Result: The obtained qualitative and quantitative characteristics-security software. Practical value: the technique of development of advanced information security systems in mobile environments such as Android. It presents an approach to the description of behavioral malware (based on the following virus: none - wakes - Analysis of weaknesses - the action: a healthy regime or attack (threat)).