This paper explores the problem of fault-tolerant control concerning an underactuated unmanned surface vehicle affected by actuator faults and disturbances in the physical layer and multiple cyber threats (time-varying delays, injection attacks, and deception attacks) in the networked layer. Firstly, an extended state observer is designed to estimate the relative state and fault information by constructing the estimation error term based on the output information affected by injection attack and delay. Secondly, a novel fault-tolerant controller is designed to deal with random Bernoulli deception attacks and compensate for time-varying delay and actuator faults by using the estimated information and considering the probability dynamics of deception attacks. Assuming that dual-channel asynchronous independent injection and deception attacks occur on the sensor-to-observer and observer-to-controller channels. A sufficient condition for asymptotic stability of the unmanned surface vehicle is derived by using Lyapunov-Krasovskii functional within the co-design framework of fault estimation and fault-tolerant control, and ensured by eliminating the equality constraint. Finally, the efficacy of the proposed algorithm is assessed through simulations of the unmanned surface vehicle under two distinct scenarios: low forward speed and high forward speed.

Unmanned Aerial Vehicles (UAVs) are pivotal in enhancing connectivity in diverse applications such as search and rescue, remote communications, and battlefield networking, especially in environments lacking ground-based infrastructure. This paper introduces a novel approach that harnesses Multi-Agent Deep Reinforcement Learning to optimize UAV communication systems. The methodology, centered on the Independent Proximal Policy Optimization technique, significantly improves fairness, throughput, and energy efficiency by enabling UAVs to autonomously adapt their operational strategies based on real-time environmental data and individual performance metrics. Moreover, the integration of Distributed Ledger Technologies with Multi-Agent Deep Reinforcement Learning enhances the security and scalability of UAV communications, ensuring robustness against disruptions and adversarial attacks. Extensive simulations demonstrate that this approach surpasses existing benchmarks in critical performance metrics, highlighting its potential implications for future UAV-assisted communication networks. By focusing on these technological advancements, the groundwork is laid for more efficient, fair, and resilient UAV systems.

The electromagnetic (EM) target situation map can visualize the situation and locations of multiple EM targets in the three-dimensional (3D) space. It is vital for the spectrum activity monitoring, radiation source localization, frequency resource management, and so on. Traditional studies focused on the radio environment map construction, and the characteristics such as locations of EM targets are not accurate due to reconstruction deviation and environmental noise. This paper presents a 3D EM target situation map construction scheme based on multiple unmanned aerial vehicle collaboration. Firstly, an improved maximum and minimum distance clustering-based algorithm is proposed to estimate the number and rough location of EM targets directly by utilizing the original sparse sampling data. Then, to improve the accuracy of situational awareness, a re-weighted map fusion algorithm is used to update the raw EM characteristics results. Finally, we calculate the self-information of different targets and optimize the previous location results. Compared with other conventional methods, numerical results demonstrate that the proposed method has higher mapping accuracy under the same low sampling rate.

This paper presents a comprehensive analysis of the shift from the traditional perimeter model of security to the Zero Trust (ZT) framework, emphasizing the key points in the transition and the practical application of ZT. It outlines the differences between ZT policies and legacy security policies, along with the significant events that have impacted the evolution of ZT. Additionally, the paper explores the potential impacts of emerging technologies, such as Artificial Intelligence and quantum computing, on the policy and implementation of ZT. The study thoroughly examines how Artificial Intelligence can enhance ZT by utilizing Machine Learning algorithms to analyze patterns, detect anomalies, and predict threats, thereby improving real-time decision-making processes. Furthermore, the paper demonstrates how a chaos theory-based approach, in conjunction with other technologies such as eXtended Detection and Response, can effectively mitigate cyberattacks. As quantum computing presents new challenges to ZT and cybersecurity as a whole, the paper delves into the intricacies of ZT migration, automation, and orchestration, addressing the complexities associated with these aspects. Finally, the paper provides a best practice approach for the seamless implementation of ZT in organizations, laying out the proposed guidelines to facilitate organizations in their transition towards a more secure ZT model. The study aims to support organizations in successfully implementing ZT and enhancing their cybersecurity measures.

Transportation and logistics systems are becoming increasingly complex and critical to modern infrastructure. This paper proposes a novel AI-enhanced fault-tolerant control framework to address the dual challenges of physical malfunctions and cyber threats. By leveraging advanced machine learning algorithms and real-time data analytics, the proposed methodology aims to enhance the reliability, safety, and security of transportation and logistics systems. This research explores the foundations and practical implementations of AI-driven anomaly detection, predictive maintenance, and autonomous response systems. The findings demonstrate significant improvements in system resilience and robustness, making a substantial contribution to the field of intelligent transportation management.

Path loss (PL) is a significant channel parameter for the link budget in unmanned aerial vehicle-aided communications. This study introduces an innovative neural network model to estimate PL for air-to-ground communication links. Utilizing the geometric characteristics of varied physical environments, the model accurately predicts PL in diverse communication scenarios. A back-propagation neural network technique is introduced for extrapolating PL under both line-of-sight and non-line-of-sight conditions. A dataset acquisition strategy, comprising scenario reconstruction and advanced ray-tracing techniques, is employed to foster the model’s training and evaluation. Finally, the proposed model is fully trained in diverse communication scenarios, and then used to predict the PLs in a new communication scenario generated by the International Telecommunication Union standard at 28 GHz. The results demonstrate that the extrapolated PLs of the proposed model are well consistent with the reference results. As existing PL models and standard PL models aim at several specifically defined scenarios, the proposed model can predict the PLs in some undefined and unknown scenarios.