Intelligent decision support systems in cybersecurity: from fuzzy logic to LLM agents

Abstract

The monograph presents a holistic scientific concept of intelligent cybersecurity management at the enterprise level. The mathematical apparatus of hierarchical structuring of security parameters and strategic selection of protection systems using the analysis of hierarchies (AHI) method by T. Saati is highlighted. The development of decision support systems (DSS) based on the Mamdani fuzzy inference algorithm in the MATLAB environment is described in detail. Decentralized multi-agent systems built on the basis of the cooperative problem solving (CPS) model and optimized by auction algorithms for task distribution based on the “regret” criterion are considered. Special attention is paid to the integration of autonomous artificial intelligence agents and the development of corporate search-augmented generation (Agentic RAG) systems for proactive detection of zero-day threats and anomalous user behavior. The publication is intended for scientists, cybersecurity and information protection specialists, developers of intelligent systems, as well as graduate students and senior students in relevant specialties.