Network security dynamic defense decision-making method based on space-time game

Abstract

The invention belongs to the technical field of network security, and relates to a network security dynamic defense decision-making method based on space-time game. The network security dynamic defense decision-making method comprises the steps of: constructing a multi-dimensional transformation moving target defense model according to network attack and defense dynamic space-time confrontation characteristics, wherein an attack party and a defense party in the multi-dimensional transformation moving target defense model are jointly determined by a detection surface, an attack surface and a detection surface through a network surface for implementing attack and defense strategy control; according to the multi-dimensional transformation moving target defense model, analyzing an attack and defense game process and describing a moving target defense security state evolution process; analyzing a continuous network attack and defense process by utilizing differential game, and constructinga moving target defense space-time decision-making model; and for the moving target defense space-time decision-making model, determining an optimal space-time defense strategy by quantifying attack and defense benefits and solving a saddle point equalization strategy. Based on the game model, the defense decision considering a space strategy and a time strategy is realized, the pertinence and timeliness of the network security defense decision are enhanced, and the network security defense efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of network security, in particular to a network security dynamic defense decision-making method based on space-time game. Background technique [0002] At present, all kinds of adaptive network attacks are becoming more and more complex and diverse. Among them, Advanced Persistent Threats (APTs) pose great challenges to traditional defense technologies due to their concealment and persistent attack characteristics. The inherent time, cost and information asymmetry characteristics of network offensive and defensive confrontation have won great advantages for attackers. In order to break this asymmetrical situation, Moving Target Defense (MTD) emerged as a very subversive active defense method. Its core idea is to reduce the homogeneity, static and deterministic This property increases the difficulty for an attacker to successfully attack. MTD research should answer the following three questions: (1) spatial...

AI Technical Summary

Problems solved by technology

However, most of the existing MTD decision-making research focuses on spatial decision-making (What to Move), and various game methods have been proposed for MTD spatial decision-making frameworks, but the equally important time decision-making (When to Move) has been simplified or ignored. At present, some researchers have begun to study the time decision-making problem, and proposed the MTD space-time decision model based on the Stackelberg game. However, the game model proposed by this method still uses a discrete multi-stage game model, and it is difficult to accurately and effectively describe the continuous state space of the MTD offensive and defensive decision-making process. Therefore, On the defense side, the selection of optimal defense decisions cannot be continuously guided, thereby affecting network defense performance

Images