基于强化学习的CBTC系统信息安全风险评估方法  

Cyber security risk assessment method of CBTC system based on reinforcement learning

作　　者：李宁 LI Ning(Beijing Metro Technology Development Co.,Ltd.,Beijing 101399,China)

机构地区：[1]北京地铁科技发展有限公司,北京101399

出　　处：《电子设计工程》2024年第6期151-155,共5页Electronic Design Engineering

摘　　要：城市轨道交通属于十分重要的基础设施,具有较高的安全苛求特性,其核心的列车运行控制系统信息安全是当前的研究热点。该文采用了复杂网络和强化学习等方法,研究了当前城市轨道交通中应用最为广泛的基于通信的列车运行控制(Communication Based Train Control,CBTC)系统的信息安全风险。分析了CBTC系统的信息安全风险要素;基于复杂网络理论构建了CBTC系统的信息域模型;研究了CBTC系统的信息安全风险量化方法,并基于强化学习评估了系统最严峻的风险面。经过实例验证,提出的方法能够有效评估CBTC系统的信息安全。Urban rail transit is important infrastructure with high security requirements,and the cyber security of train control system is also a hot research direction at present.In this paper,the cyber security risks of Communication Based Train Control(CBTC)system,which is widely used in urban rail transit,are studied by using complex network and reinforcement learning methods.The cyber security risk elements of CBTC system is analyzed;The cyber model of CBTC system is built based on complex network theory;The quantification method of cyber security risk of CBTC system is studied,and the most severe risk of the system is evaluated based on reinforcement learning.It has been verified that the method can effectively evaluate cyber security of CBTC system.

关 键 词：轨道交通 CBTC系统 信息安全 复杂网络 强化学习 

分 类 号：TN915.08[电子电信—通信与信息系统]