Traffic Analysis Based Identification of Attacks

This paper is devoted to the problem of identification of network attacks via traffic analysis. Neural networks are chosen by us due to their capability to recognize an attack, to differentiate one attack from another, i.e. classify attacks, and, most important, to detect new attacks that were not included into the training set. Performed experiments demonstrate the advantage of our intrusion detection system compared to those created by the winner of the KDD Cup the leading data mining and knowledge discovery competition in the world. The results obtained indicate that it is possible to recognize attacks that the intrusion detection system never faced before on an acceptably high level.