DEVELOPMENT OF A NETWORK ATTACK DETECTION SYSTEM

Selin Andrey Alexandrovich, Blinov Vladimir Vladimirovich, Amelyutin Evgenij Vyacheslavovich

The article is devoted to the development of a network attack detection system that uses a method combining a multilayer perceptron, gradient boosting and a KNN algorithm. The dataset used in the work includes various types of attacks, such as DoS (denial of service), R2L (unauthorized access to the local system), U2R (access enhancement) and Probe (system scan). The proposed solutions can be effectively used in financial institutions, government agencies, medical organizations and corporate networks, where it is critically important to maintain a high level of cybersecurity.

Keywords:intrusion detection system, information security, network attacks, traffic monitoring.