As unmanned aerial vehicle (UAV) applications expand across logistics, agriculture, and emergency response, safety and security threats are becoming increasingly complex. Addressing these evolving threats, including physical safety and network security threats, requires continued advancement by integrating traditional artificial intelligence (AI) tools such as machine learning (ML) and deep learning (DL), which contribute to significantly enhancing UAV safety and security. Large language models (LLMs), a cutting-edge trend in the AI field, are associated with strong capabilities for learning and adapting across various environments. Their emergence reflects a broader trend toward intelligent systems that may eventually demonstrate behavior comparable to human-level reasoning. This paper summarizes the typical safety and security threats affecting UAVs, reviews the progress of traditional AI technologies, as described in the literature, and identifies strategies for reducing the impact of such threats. It also highlights the limitations of traditional AI technologies and summarizes the current application status of LLMs in UAV safety and security. Finally, this paper discusses the challenges and future research directions for improving UAV safety and security with LLMs. By leveraging their advanced capabilities, LLMs offer potential benefits in critical domains such as urban air traffic management, precision agriculture, and emergency response, fostering transformative progress toward adaptive, reliable, and secure UAV systems that address modern operational complexities.

Although resource sharing and mixed numerology among slices are promising for improving wireless resource utilization, these techniques can compromise isolation performance and cause serious inter numerology interference (INI). Therefore, this paper studies wireless resource management in a mixed numerology-based sliced 6G space–terrestrial integrated radio access network (STI-RAN) with the aim of reducing INI and guaranteeing isolation performance while decreasing interference from Doppler frequency shifts caused by the high-speed movement of low-orbit satellites. First, an isolation performance indicator is defined to evaluate different isolation performances, and a universal spectral distance model is formulated to rewrite the INI power model. Next, the dynamic wireless resource management problem is formulated in a discrete form, yielding a scheme called Flex- $\mu$ , which is designed to reduce the INI and Doppler frequency shifts, guarantee isolation performance, and enhance the SINR. Finally, an intelligent multi-characteristic matrix coding-based social group optimization (MultiMatrix-SGO) algorithm is designed to solve the proposed NP-hard discrete optimization problem. Compared with existing schemes, the system utility is efficiently increased by up to 58.32%, the SINR can converge to 38.44dB, and the isolation performance is guaranteed while the INI and Doppler frequency shifts are reduced

In the fifth generation (5G) networks, isolated logical slices are formed by the same infrastructure and spectrum resource. In the coverage regions of the sharing access points (APs), device to device (D2D) communication can occur among different slices, i.e., one mobile terminal (MT) acts as a D2D relay for another MT serving by a different slice. Since the slices and the MTs are selfish who will not help others voluntarily, this paper proposes a two-layered incentive scheme to stimulate cooperation. To achieve this, two resource allocating problems of the proposed incentive scheme are formulated which introducing the slices' and the MTs' cooperative activities, thus more resources will be allocated to the cooperative slices and MTs as reward. Since the slices' and the MTs' instantaneous resource allocations can not be obtained by the two optimal problems, the incentive scheduling algorithms of the slices and the MTs are designed. Finally, we define the isolation indexes to evaluate the slice isolation when carrying out cooperation. By simulating, it is proved that the proposed incentive scheme can stimulate cooperation efficiently, since the throughputs of the cooperative slices and MTs are both improved. And the proposed incentive scheme is helpful for the slices and the MTs to meet the statistical service quality requirements and brings the bad effect to the instantaneous service quality requirements.

Although deep learning (DL) methods are effective for detecting protocol attacks involving drones in sixth-generation (6G) nonterrestrial networks (NTNs), classifying novel attacks and identifying anomalous sequences remain challenging. The internal capture processes and matching results of DL models are useful for addressing these issues. The key challenges involve obtaining this internal information from DL-based anomaly detection methods, using this internal information to establish new classifications for uncovered protocol attacks and tracing the input back to the anomalous protocol sequences. Therefore, in this paper, we propose an interpretable anomaly classification and identification method for 6G NTN protocols. We design an interpretable anomaly detection framework for 6G NTN protocols. In particular, we introduce explainable artificial intelligence (XAI) techniques to obtain internal information, including the matching results and capture process, and design a collaborative approach involving different detection methods to utilize this internal information. We also design a self-evolving classification method for the proposed interpretable framework to classify uncovered protocol attacks. The rule and baseline detection approaches are made transparent and work synergistically to extract and learn from the fingerprint features of the uncovered protocol attacks. Furthermore, we propose an online method to identify anomalous protocol sequences; this intrinsic interpretable identification approach is based on a two-layer deep neural network (DNN) model. The simulation results show that the proposed classification and identification methods can be effectively used to classify uncovered protocol attacks and identify anomalous protocol sequences, with the precision increasing by a maximum of 32.8% and at least 26%, respectively, compared with that of existing methods.

Non-public networks (NPNs) have drawn much attention due to their flexibility and efficiency with B5G. According to the requirements of various application scenarios, NPNs can be tailored to a number of deployments, sharing the B5G system totally or in part. The isolation of NPNs is a critical issue. This paper provides a survey of isolation schemes for B5G NPNs. First, we present an overview of various deployments and the corresponding isolation demands for B5G NPNs. To meet these isolation demands, three kinds of NPN isolation—i.e., spectrum isolation, RAN isolation and CN isolation—are discussed. Then, the corresponding isolation technologies are introduced and analyzed. Finally, open research challenges, such as wireless throughput capacity with spectrum isolation, operation with isolation requirements and data isolation of software-defined CN for B5G NPNs, are discussed.

As the 5G network continues to evolve with micro-services, the protocol implementation in the network is decentralised to individual network elements, with multiple network elements collaborating to provide services to the terminals. The functional testing of the network therefore requires the simultaneous testing of multiple network elements.The current test system cannot test multiple network elements simultaneously and has the problem that test anomalies are difficult to locate.This paper proposes a distributed testing framework for 5G networks, which is based on the TTCN-3 testing framework as a prototype and designed using keyword-driven technology and remote procedure call (RPC) technology based on C/S architecture.The framework has proven to have the following advantages: good scalability of the test nodes, the ability to test multiple network elements simultaneously, and the ability to locate test anomalies at the element signalling level.