The paper presents the results of a research of using transfer training of the capsule neural network to detect malware. The research was carried out on the basis of the source code of malware using the context-triggered piecewise hashing method. The source codes of malware were obtained from public sources of software. Verification of the capsule neural network learning results was carried out using a trained convolutional neural network, and publicly available sources of test to malware. The research was conducted on six types of malware. Software source code, part of capsule neural network training datasets, pre-trained capsule neural network, and full research are publicly available at https://github.com/T-JN.

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

The paper presents the results of calculations and tests of the developed dataset expanding algorithm for training a generative-adversarial network. The research was conducted on two types of malicious software: mimikatz and cring. The boosting method was chosen as a method for expanding the database of datasets. The process of expanding the database of datasets was carried out in a granular manner, using timestamps. Simulation of the algorithm operation at different iterations and visualization of the results have been carried out.

The paper presents the results of the research the model for changing the logistic function. The research was conducted on datasets generated based on the source code abc, cheeba, december_3, stasi, otario, dm, v-sign, tequila, flip malware source code base. Research was conducted to evaluate the accuracy of the developed intrusion detection system with machine learning. As a mathematical apparatus for the research, a multidimensional logistic function softmax was chosen. The simulation of the developed software at different iterations and visualization of the results was carried out.