Research of Algorithm for Expanding the Database of Training Datasets of a Generative-Adversarial Network

Abstract

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.