Unmanned aerial vehicle (UAV)-assisted communication networks offer an effective solution for establishing connectivity and enabling data delivery in scenarios where direct communication with terrestrial infrastructure is infeasible, such as in disaster areas. In such networks, unknown user locations, dynamic node mobility, and multi-hop transmission collectively increase the complexity of the communication process. Specifically, the uncertainty of user positions makes it difficult for UAVs to establish and maintain reliable communication links, while the mobility of both mobile users (MUs) and UAVs leads to frequent fluctuations in link quality. Furthermore, the dynamic network topology increases the complexity of routing in multi-hop transmissions, requiring UAVs to continuously adjust their trajectories to ensure stable and efficient data relaying. In this paper, we apply received signal strength indicator (RSSI)-based multilateration and deep reinforcement learning (DRL) to address the associated difficulties. Specifically, UAVs estimate the positions of nearby MUs using RSSI-based multilateration. The joint problem of mobility control and data forwarding is formulated as an Markov decision process (MDP), and a multi-agent proximal policy optimization (MAPPO) algorithm is employed to learn decentralized decision-making policies. Extensive simulations demonstrate that the proposed scheme improves transmission completion ratio and reduces transmission delay in UAV-assisted communication networks.

Network slicing, as the backbone technique of evolving B5G/6G, consists of Network Function Virtualization Infrastructure (NFVI) layer, network slice instance layer, service instance layer and management and orchestration module. Given the lessons learned from recently reported nationwide and long-lasting global telecommunication disasters with severe service degradation or even outages, we find that many of them orig-inated from a simple faulty entity in the NFVI layer at the very beginning. To the best of our knowledge, as the very first attempt, we propose Zoom-inRCL, which enables us to quickly and accurately find the root cause entity at the NFVI layer once observing the slice service degradation. Specifically, it first filters abnormal NF call graphs at the graph level based on deep support vector data description (Deep SVDD) algorithm and then filters faulty entity candidates at the node level by novelly designed rules, and finally infers the suspicious entity rank list according to the ratio of affected NFs. Evaluations on a real-world dataset show that for over 80% of fault cases, the top-ranked entity identified by Zoom-inRCL is the actual root cause of the service degradation. We believe that our work can provide useful guidance for the design of future B5G/6G networks.

Network virtualization technology is envisioned as the new paradigm for modern Internet by virtue of its flexible management and allocation of physical resources, as well as fast provisioning of customized network services. Virtual network embedding (VNE), one of the main issues faced by network virtualization, has attracted interests of numerous researches due to its importance and proven NP-hardness. However, existing works addressing this issue have limitations such as inadequate generality, heavily relying on hand-craft features, inefficient to the changeable action space of the VNE problem, etc. Towards this end, we propose a VNE scheme in this paper with a new environment interpretation mechanism and a duel network based decision making architecture, which has the automatically feature extraction ability for both physical and virtual networks, and the capability of adapting to the VNE environment with changeable action space. Comparison results with existing works demonstrate the superiority of our proposal, which can bring higher acceptance ratio and larger average revenue on both synthetic and real physical networks.

Unmanned aerial vehicles (UAVs) have shown great potential in benefiting industries due to their good features, such as the ease of deployment and low maintenance cost. However, the communication security issue remains a serious challenge before the large-scale application of industrial UAVs. The untrusted communication environment can cause the leakage of valuable industrial data or the losing of important cargos that carried by UAVs. Traditional authentication mechanisms for protecting communications include public-key infrastructure-based, ID-based, and certificateless authentication. These mechanisms rely on a central authority and some of them may introduce high-complexity computation that is not suitable for industrial drones. Therefore, aiming at these challenges, we design a blockchain-assisted distributed and lightweight authentication service for industrial UAVs. The blockchain technology supports the distributed and immutable storage of industrial UAVs’ authentication information, and smart contracts enable convenient operations for drones to acquire or update the corresponding information. Security evaluation demonstrates that our scheme is resistant to various attacks and can guarantee trustworthy communications for industrial drones. Extensive experiments also show that our designed authentication service can not only achieve low computation and communication cost for industrial UAVs but also remain robust even if a small proportion of drones are compromised.

Unmanned aerial vehicle (UAV) is recognized as one of the best sensing tools for gathering data in the industrial Internet of things sector. Besides, the flying ad hoc network (FANET) with multiple drones shows significant advantages in complicated task performing of large area. However, as an important part of communication security, key management for FANET currently depends heavily on the base station or infrastructures, which may easily become the attack target or increase the communication overheads of drones. Therefore, we propose a blockchain-based distributed key management scheme for heterogeneous FANET in this article, based on which drones can autonomously distribute cluster keys, update their public/private key pairs, migrate between clusters, and revoke malicious UAVs in a secure way. Security analysis and performance evaluation prove that our scheme can resist against a variety of external and internal attacks, and guarantee lightweight energy consumption for ordinary drones in the network.

The development of vehicular networks spawns various service scenarios, whether safety-related or infotainment-related, making people's life and travel more comfortable and efficient. As an innovative network architecture to realize centralized control, Software-Defined Networking (SDN) is very beneficial to the management of complex vehicular networks. Nevertheless, its security has received little attention. If the core SDN controller is threatened, the entire vehicular network can be seriously affected. To this end, we focus on the vulnerability of SDN controller, successfully perform topology poisoning attacks on four mainstream controllers, analyze the attack impacts hierarchically, and discuss the countermeasures for security improvement. As far as we know, we are the first to explore the security of SDN controller in vehicular networks.

With the development of Internet and communication technologies, various information can easily spread to children via applications (Apps) on Internet-of-Things (IoT) devices (e.g., emerging smart toys, watches, and phones), especially, the Apps on smart phones based on Android. While greatly bringing up convenience for children's lives and studies, these Apps also make illegal and inappropriate contents (such as violence, pornography, gambling, and drug) more accessible to kids, which is harmful to minors' growth. To keep children away from inappropriate contents in applications, previous researches mainly focused on detecting unsuitable videos and advertisements in children applications or designing App maturity rating methods and parental control software. There are few literature that specially investigate the inspection of inappropriate contents in children Android Apps. Toward this end, we propose a novel automatic content inspection and the forensics framework to identify children Android Apps which are not proper for kids under 12. In addition, this framework offers evidence to make users understand why the inspected App is judged as unsuitable. In experiments, we apply this framework on some specially chosen Android Apps which distinctly include inappropriate contents to verify its performance. The results show that it can successfully identify those applications with high precision that reaches 85.7%. Besides, by analyzing the collected children's Android Apps through our framework, we find that 40% of them are identified to be improper, which illustrates the serious issue of unsuitable children Android Apps.

The development of the Internet of Vehicles (IoV) has made people's lives and travels safer, more efficient, and more comfortable. The combination of edge computing and IoV can provide processing and storage capabilities close to vehicles, thus becoming a potential paradigm. At this time, the software-defined networking (SDN) architecture is extremely necessary to realize centralized control and convenient management for complex and dynamic vehicular edge networks. However, as the brain of the SDN architecture, little attention has been paid to the security of the SDN controller. Once the controller is threatened, severe global chaos may happen. Therefore, in this article, we study the attack against the SDN controller, which is the topology poisoning attack. We successfully implement this attack in four mainstream controllers and analyze its impact from multiple levels. To the best of our knowledge, we are the first to study this attack in the vehicular edge network. In addition, in view of the counter-attacks of the existing defence mechanisms, we propose an attack-tolerance scheme based on deep reinforcement learning (DRL) to enhance the vehicular edge network with a certain degree of self-recovery.