Although a cyber-physical system (CPS) enhances the system control flexibility by connecting physical devices to the network, it also increases the possibility of network attacks on the system, which can cause damage to both property and personnel. To achieve CPS security, this paper proposes a network security protection method based on a digital twin (DT). By constructing DT models of the CPS physical layer and network layer and collecting real-time data of the system, the system security is improved from several aspects. First, we construct a data-driven behavior model for the CPS physical layer and introduce expert knowledge in order to realize the function of physical layer anomaly diagnosis. Comparisons with related studies show that our method achieves a higher precision, recall rate, and F1 score. Second, we construct an attack graph model for the CPS network layer for CPS network security analysis in order to realize the functions of security risk quantification and security countermeasure recommendation. Finally, we model the interaction between the physical networks and transfer the diagnosis results of the physical layer twin to the network layer twin in order to correct the attack graph. Thus, we achieve an accurate representation of the overall network security situation in real time.

The rapid development of the Internet of Things (IoT) requires network automation, to improve management efficiency and reduce manual operations. Zero-touch network is a promising technology for empowering network management automation by creating virtualized networks for software-based solutions. However, the traditional software-defined network (SDN) technology is not suitable for IoT devices, due to its massive, heterogeneous, and distributed characteristics. In this paper, we introduce digital twin technology (DT) into the IoT, and propose a DT modeling method through ontology and knowledge graph technologies, which maps IoT elements in the digital space and provides the advantages of centralized control, device abstraction, and flexible control of management. Then, referring to the conceptual architecture of a zero-touch network, a DT-based zero-touch management framework suitable for IoT is established. Finally, aiming at specific device management and network optimization problems in the IoT, a zero-touch management scheme with digital twin technology as the core and intention as the driver is proposed, and the effectiveness of the proposed method is demonstrated using an example.