An automated security policy generation method based on rule-matching and machine-learning models

With the increasing diversification of security threats and the expanding scale of industrial control system networks, traditional manual policy generation methods are inadequate for the swift response required and are prone to configuration errors. An automated security policy generation method is proposed in this paper, integrating rule-matching with machine learning models to dynamically adapt to network security conditions, thereby effectively enhancing response speed and accuracy. By minimizing human intervention, the method reduces the risks associated with misconfiguration errors and employs machine learning algorithms for precise identification and response to security threats, offering more robust security protection for industrial control systems.