No abstract

With the rapid enhancement of computer computing power, deep learning methods, e.g., convolution neural networks, recurrent neural networks, etc., have been applied in wireless network widely and achieved impressive performance. In recent years, in order to mine the topology information of graphstructured data in wireless network as well as contextual information, graph neural networks have been introduced and have achieved the state-of-the-art performance of a series of wireless network problems. In this review, we first simply introduce the progress of several classical paradigms, such as graph convolutional neural networks, graph attention networks, graph autoencoder, graph recurrent networks, graph reinforcement learning and spatial-temporal graph neural networks, of graph neural networks comprehensively. Then, several applications of graph neural networks in wireless networks such as power control, link scheduling, channel control, wireless traffic prediction, vehicular communication, point cloud, etc., are discussed in detail. Finally, some research trends about the applications of graph neural networks in wireless networks are discussed.

With the promotion of Industry 4.0, which emphasizes interconnected and intelligent devices, several factories have introduced numerous terminal Internet of Things (IoT) devices to collect relevant data or monitor the health status of equipment. The collected data are transmitted back to the backend server through network transmission by the terminal IoT devices. However, as devices communicate with each other over a network, the entire transmission environment faces significant security issues. When an attacker connects to a factory network, they can easily steal the transmitted data and tamper with them or send false data to the backend server, causing abnormal data in the entire environment. This study focuses on investigating how to ensure that data transmission in a factory environment originates from legitimate devices and that related confidential data are encrypted and packaged. This paper proposes an authentication mechanism between terminal IoT devices and backend servers based on elliptic curve cryptography and trusted tokens with packet encryption using the TLS protocol. Before communication between terminal IoT devices and backend servers can occur, the authentication mechanism proposed in this paper must first be implemented to confirm the identity of the devices and, thus, the problem of attackers imitating terminal IoT devices transmitting false data is resolved. The packets communicated between devices are also encrypted, preventing attackers from knowing their content even if they steal the packets. The authentication mechanism proposed in this paper ensures the source and correctness of the data. In terms of security analysis, the proposed mechanism in this paper effectively withstands replay attacks, eavesdropping attacks, man-in-the-middle attacks, and simulated attacks. Additionally, the mechanism supports mutual authentication and forward secrecy. In the experimental results, the proposed mechanism demonstrates approximately 73% improvement in efficiency through the lightweight characteristics of elliptic curve cryptography. Moreover, in the analysis of time complexity, the proposed mechanism exhibits significant effectiveness.

Due to the incompleteness of knowledge map, the existing knowledge map is usually missing, and the task of knowledge reasoning is to predict the missing facts according to a large number of information such as entities and relationships. In order to satisfy the interpretability and accuracy, this paper proposes a multi-hop reasoning method combining first-order logic and graph embedded vector, which has the mathematical rigor of logical reasoning and the high accuracy of embedded vector. For the specified query, it is transformed into a first-order logical operation representation, and the query dependency graph is instantiated, and the reverse sampling from the root node to the anchor point in the instantiation process ensures that the query must have an answer. According to the query calculation diagram combined with logical operators, reasoning is based on embedded method, which avoids explicitly traversing KG and obtains the query answer.