Research of Model Increasing Reliability Intrusion Detection Systems

Abstract

The paper presents the results of the using, a recurrent neural network to detect malicious software as part of the Snort intrusion detection system.The research was conducted on datasets generated on the basis of athena, dyre, engrat, grum, mimikatz, surtr malware exploiting vulnerability CVE-2022-20685 in the Snort intrusion detection system. Processing of input traffic data was carried out before the frag-3 and modbus preprocessors. The method of k nearest neighbors was used as a mathematical apparatus. The simulation of the developed software at different iterations. All research results are presented in https://github.com/T-JN