The method of abnormality detection caused by cyber attacks in computer networks

Abstract

One of the security solutions are intrusion detection systems, constructed on the principles of abnormality. Such systems are usually based on mathematical methods that require a lot of time to produce statistics. There is therefore a need for more effective methods based on peer-based approaches. For this task solution it is proposed the method based on mathematical models and methods of fuzzy logic, and containing eight basic steps (method selection of fuzzy data processing; selection of how to define the importance factor, formation of sets of attacks and parameters, formation of standards parameters, formation of multiple heuristic rules, definition of matrix initialization, formation of result) that show the process of abnormal condition detection, generated by a specific type of cyber-attacks in the IS. This method can be used to create or improve existing systems of cyber attacks detection in computer networks.