Time dependent network resource optimization in cyber-physical systems using game theory

Abstract The social and economic stability of a country is dependent on critical infrastructures (CIs) whose services range from financial to healthcare and power to transportation and communications. Most of these CIs are cyber-physical systems (CPSs), which integrate the network’s computational and communication capabilities to facilitate the monitoring and controlling of physical processes. Such systems are vulnerable to damage due to natural disasters, physical incidents, or cyber-attacks impacting the CPS organizations managing complex industrial control systems and data acquisition systems. When these CPSs are exposed to systemic cyber risks and cascaded network failures, network administrators need to recover from the compromise under limited resources. This is formulated as an attacker-defender game model to emulate the decision-making process in choosing an appropriate attack/defence mechanism in response to cybersecurity incidents using game theory. To further improve the assumptions made in the pure game-theoretic model, we relax the constraints on the rationality of the players, monetary payoff, and completeness of information by incorporating learning in games using reinforcement learning technique and compute the expected payoff using linguistic fuzzy variables.