Network active defense policy selection method and device based on Bayesian evolutionary game

Abstract

The invention belongs to the technical field of the network security, and especially relates to a network active defense policy selection method and device based on Bayesian evolutionary game. The method comprises the following steps: constructing a network attack Bayesian evolutionary game model according to an incomplete information game scene in an actual attack-defense adversarial network; setting a selection strength factor for describing gamer learning capacity, and constructing a random replicate dynamic equation about the attacker-defender policy evolution; combining the random replicate dynamic equations about the attacker-defender policy evolution, solving to acquire a stable balance point of the attacker-defender policy evolution, and determining and outputting an optimal defense policy. From the limited intellectual visual angle of the participant, a replicate dynamic equation about the participant decision process is constructed and solved by means of the replicate dynamicmechanism for describing the biological evolution, the method is suitable for incomplete information network attack-defense adversarial network and more suitable for the actual application, the generality and operability in the network decision implementation process are enhanced, and the effective guidance is provided for selecting the active defense policy.

Description

technical field [0001] The invention belongs to the technical field of network security, in particular to a method and device for selecting a network active defense strategy based on Bayesian evolutionary game. Background technique [0002] With the rapid development of science and technology and economy, especially the rapid development of network information systems, sudden changes have taken place in the way of information collection and exchange. Due to the increasingly complex and dynamic network systems, security attacks emerge in endlessly, and the security situation is becoming increasingly severe. Security issues are highly concerned by academia, industry and government. Considering the limited hardware resources of network equipment, there are certain limitations in terms of computing power and storage capacity, and as the attack methods become more and more complex, how to adopt corresponding levels of security defense strategies according to different levels of a...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the deficiencies in the prior art, the present invention provides a method and device for network active defense strategy selection based on Bayesian evolutionary game, which solves the problem that only complete information conditions are considered in the prior art, and the inconsistencies existing in the actual attack-defense confrontation process are not considered. In the case of symmetric information and unsatisfactory model operability, the model is constructed based on the incomplete information game situation, and the strategic income of both the attacker and the defender is taken as the uncertainty of both the attacker and the defender. Provide preventive measures to further improve network security performance

Images