Network Defense Decision-Making Based on Deep Reinforcement Learning and Dynamic Game Theory

作     者：Huang Wanwei Yuan Bo Wang Sunan Ding Yi Li Yuhua Huang Wanwei;Yuan Bo;Wang Sunan;Ding Yi;Li Yuhua

作者机构：College of Software EngineeringZhengzhou University of Light IndustryZhengzhou 450001China The Third Construction Co.Ltd of China CREC Railway Electrification Engineering GroupZhengzhou 450052China Electronic and Communication EngineeringShenzhen Polytechnic UniversityShenzhen 518055China 

出 版 物：《China Communications》 (中国通信（英文版）)

年 卷 期：2024年第21卷第9期

页      面：262-275页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 080402[工学-测试计量技术及仪器] 0804[工学-仪器科学与技术] 070105[理学-运筹学与控制论] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the Major Science and Technology Programs in Henan Province(No.241100210100) The Project of Science and Technology in Henan Province(No.242102211068,No.232102210078) The Key Field Special Project of Guangdong Province(No.2021ZDZX1098) The China University Research Innovation Fund(No.2021FNB3001,No.2022IT020) Shenzhen Science and Technology Innovation Commission Stable Support Plan(No.20231128083944001) 

主　　题：A3C cyber attack-defense analysis deep reinforcement learning stochastic game theory 

摘      要：Existing researches on cyber attackdefense analysis have typically adopted stochastic game theory to model the problem for solutions,but the assumption of complete rationality is used in modeling,ignoring the information opacity in practical attack and defense scenarios,and the model and method lack *** such problem,we investigate network defense policy methods under finite rationality constraints and propose network defense policy selection algorithm based on deep reinforcement *** on graph theoretical methods,we transform the decision-making problem into a path optimization problem,and use a compression method based on service node to map the network *** this basis,we improve the A3C algorithm and design the DefenseA3C defense policy selection algorithm with online learning *** experimental results show that the model and method proposed in this paper can stably converge to a better network state after training,which is faster and more stable than the original A3C *** with the existing typical approaches,Defense-A3C is verified its advancement.