The present paper describes some of the results obtained in the Faculty of Computer Systems and Technology at Technical University of Sofia in the implementation of project related to the application of intelligent methods for increasing the security in computer networks. In order to build a rational and consistent approach to the choice of artificial intelligence methods best suited to counteract certain classes of threats, it is necessary to achieve systematization, unification and classification of the cyber-security threats and the sources of these threats. This can be realized using the new concepts and classifications in the field of cyber threats examination.