Nowadays, networks are not fully automated due to complex and complicated issues that have not been solved for a long time. In order to bring the network closer to automation, such problems as unsupervised searches for intrusions and malicious attacks must be resolved. Modern and cutting-edge ways to hack the network, intercept traffic, and plant malicious programs appear daily, making research even more difficult. Currently, we need unique and universal ways to identify interventions in networks. New comprehensive solutions must have self-controlled systems that can work autonomously and stop intrusions, heal the system, predict new vulnerable places of the networks, and prognosticate new ways of intrusions into the software-defined networks. Furthermore, current traffic is passed in massive amounts, and data representation types vary from vendor to vendor of network devices. Such problems as storage, processing, bringing the data to the same kind of representation, and creating self-supervised learning play a tremendously significant role. This article reviews different ways of using a genetic algorithm, fuzzy logic, or more precisely, fuzzy inference, fuzzy interpolation, and fuzzy clustering. Fuzzy logic-based solutions might not only be overlooked for the exposure of intrusions and malicious activities in the networks, but they can also help with an extensive range of problems of Big Data and help to balance the data and enhance processing and sorting it. Keywords: intrusion detection system, information security, fuzzy logic, fuzzy inference, fuzzy clustering.