DESIGN OF ADAPTIVE SYSTEM FOR DETECTION OF CYBER-ATTACKS

This paper is devoted to the improvement of the mathematical support for the intelligent detection models of cyber threats. The results of the research present the further development of detection models of cyber threats, as well as of common classes of cyber-attacks in mission critical information systems (MCIS). There was the model of detection of cyber-attacks to MCIS designed, which is based on the application of learning samples in the form of matrices of features for each of the modeled classes. The studies on minimization of the number of training samples, represented by a binary form of discerning features were carried out. There was the program "Cyber-attacks Analyzer” developed, which allows the automatic generation of dimensions of training matrix of cyber-attacks features, without requiring the participation of experts. It is shown that for the object detection within known classes of cyber-attacks the usage of representative sets of 3-4 features long in the training matrices increases the effectiveness of the algorithm, reaching up to 95%.