Dynamic Awareness of Network Security Situation Based on Stochastic Game Theory

摘要

Stochastic game theory is proposed to apply in the research on network security situational awareness (NSSA), which is a research focus in network security field at present. A novel dynamic awareness method of network security situation (NSS) based on analyses of network service states is proposed in this paper. Realizing situation awareness is a dynamic process, and the diverse states of network services are just direct mirrors of the whole network security situation. Network security situation reflects what is happening in the network, including both the offense and defense behaviors in it. Stochastic game model of network security system is constructed in this paper, and network security situation is quantified by the game mathematical formulation, costs or rewards of attackers and defenders are established, and finally non-linear programming is used to compute the Nash equilibrium points, at which point both of the two sides get a balance between their benefits. Network security situation can then be dynamically achieved by visualizing the diverse metrics information of network services at Nash equilibrium during the operating of network system.