Automatic fine-grained access control in SCADA by machine learning

The access control is one of the core technique to ensure safety and privacy of the sensing data in information systems. Supervisory control and data acquisition (SCADA) is a very security primitives in control system architecture that are being applied to computers, networked data communications and graphical user interfaces for high-level process supervisory management. SCADA infrastructure which is an essential part of metro systems have been studied by many researchers in recent years. In this paper, We introduce several access control techniques such as Role-Based Access Control (RBAC), Attribute-Based Access Control (ABAC), Fine-Grained Access Control (FGAC). Brief literature review is provided, and possible improvements over the state-of-the-art access control techniques are also proposed. Specially, the machine learning techniques is introduced, which is potential to automate the tedious role engineering process.