基于贝叶斯攻击图的工控系统动态风险评估

Dynamic risk assessment of industrial control system based on bayesian attack graph

针对工业控制系统信息安全动态风险评估问题,将攻击图与贝叶斯理论结合,提出一种基于贝叶斯攻击图的工业控制系统信息安全动态风险评估模型。基于贝叶斯攻击图网络结构,结合先验分布和入侵检测系统获得的实时攻击样本数据运用贝叶斯参数学习对节点条件概率表进行动态调节,实现对目标网络整体安全性的动态风险评估。仿真结果分析证明了该模型的有效性和准确性,可为实施动态安全防护策略提供决策依据。

Aiming at the cyber security risk assessment of the industrial control system, this paper combines the attack graph with Bayesian theory and proposes a dynamic risk assessment model of information security based on Bayesian attack graph in industrial control system. Based on the network structure of Bayesian attack graph, real time attack sample data from intrusion detection system are used as the inferring evidence of Bayesian attack graph, and the conditional probabilities of the nodes are adjusted accordingly, thus the cyber security risk of the target industrial control system can be assessed dynamically. The simulation verifies the feasibility and accuracy of the proposed method which can provide decision-making support for dynamic cyber security protection.