VTC 2025 Spring Conference’s Shorts

ADSecData Platform: An Open-Source Data Platform for Autonomous Driving Cybersecurity

Autonomous driving (AD) software needs to be secure, and its decision control must be robust against cyber threats. The development of cybersecurity solutions for legacy and connected vehicles has been supported by an array of open-source datasets, mainly focused on the CAN Bus protocol. There exists a lack of open-source cybersecurity data and community-driven platforms that enable fair and reproducible evaluations of AD algorithms from a cybersecurity perspective and defensive mechanisms. This study addresses this problem by conducting an in-depth analysis of the data ecosystem for AD cybersecurity and introducing an initial open-source data platform, ADSecData. ADSecData offers the community a comprehensive 4-stage method for the creation of AD cybersecurity datasets, along with an initial common dataset. We evaluate the utility of ADSecData through a case study featuring diverse malicious injection attacks, including GPS spoofing, LiDAR point-cloud manipulation, and sensor interference. The results demonstrate the viability of ADSecData in generating AD cybersecurity datasets and supporting community research and development.ADSecData Platform: An Open-Source Data Platform for Autonomous Driving CybersecurityAndrew Roberts, Mohsen Malayjerdi, Tallinn University of Technology; Mauro Bellone, FinEst Centre for Smart Cities; Raivo Sell, Tallinn University of Technology; Olaf Maennel, University of Adelaide; Mohammad Hamad, Sebastian Steinhorst, Technical University of Munich

A Personalized Federated Imitation Learning Algorithm for Autonomous Driving

Currently, end-to-end autonomous driving systems that employ imitation learning effectively learn and optimize driving strategies by integrating the driving behaviors of human experts with modern deep learning techniques. However, challenges such as scene diversity, data security, and training time must still be addressed to develop a model that is applicable across various traffic scenarios while maintaining high accuracy. To tackle these issues, this paper proposes a personalized federated imitation learning algorithm that aggregates locally trained imitation learning decision models from vehicles operating in different scenarios through a distributed training approach, thereby enhancing training efficiency and model accuracy. Specifically, considering the variability in communication link quality and potential disconnections caused by the mobility of vehicles in a connected vehicle network, we introduce a personalized user selection algorithm. Building on this foundation, we employ a federated imitation learning method to efficiently and rapidly train a driving decision model with comparable performance while safeguarding data privacy. Extensive simulation results confirm the superiority of the proposed algorithm in terms of training speed and model accuracy.A Personalized Federated Imitation Learning Algorithm for Autonomous DrivingJiangtao Lv, Yuchuan Fu, Changle Li, Nan Cheng, Ruijin Sun, Xidian University

Validating an LTE V2X Congestion Simulation with Field Test Data

The increasing number of traffic fatalities motivates adoption of vehicular communication technologies. Long Term Evolution (LTE) vehicle-to-everything (V2X) technology automatically exchanges information among and between vehicles and infrastructure to enable safe and efficient transportation services. To understand the performance of LTE V2X technology, the U.S. Department of Transportation conducted field tests in 2021 and 2022. A simulation tool was developed to provide a more cost-effective solution for assessing LTE V2X performance in a diverse range of scenarios and LTE V2X configurations. In this study, the packet error rate (PER) results found in field tests were compared with those produced in simulations for three different test types: static devices (SDs) with fixed transmit time interval (TTI) of 100 ms, SDs with fixed TTI of 600 ms, and SDs with congestion control (CC) ON. It was found that although simulation results sometimes fall outside the confidence bars on the 100 ms TTI case, they stayed within the 95% confidence intervals of the field test on the 600 ms TTI and CC cases. Thus, the simulation demonstrated results that were in line with the field trial measurements. Simulation results were also extended to compare cases with 1,500 devices with CC ON and 252 devices with 100 ms TTI.Validating an LTE V2X Congestion Simulation with Field Test DataMustafa Yilmaz, National Telecommunications and Information Administration

Universal Scanning GUI Tool for Available and Usable TV White Space (TVWS) Spectrum

The TV white space (TVWS) technology has proven to be effective and feasible in connecting rural and hard-to-reach areas to Internet service. The TVWS wireless systems operate based on geolocation white space databases (WSDB) to protect the primary systems from harmful interference and thus there is a critical need to know the available and usable channels that can be used by the secondary users in a specific geographic area. In this work, we developed a generalized and flexible universal graphical user interface (GUI) tool to evaluate the availability and usability of the TVWS channels and their noise levels in any specific geographical area. The developed tool has many features and capabilities such as scanning the TVWS spectrum for any geographical area in the world and any TVWS frequency band. Moreover, it allows the user to apply widely used terrain-based radio propagation models. It provides flexibility in importing the elevation terrain profile of any region with the desired spatial accuracy and resolution. In addition, various system parameters including regulation rules can be modified in the tool. This tool exports to an external dataset file the output data of the available and usable channels and their noise levels and it also visualizes these data interactively.Universal Scanning GUI Tool for Available and Usable TV White Space (TVWS) SpectrumMUNEER ALZUBI, King Abdullah University of Science and Technology (KAUST); Mohamed-Slim Alouini, King Abdulah University of Sience and Technology (KAUST)

CNN+Transformer Based Anomaly Traffic Detection in UAV Networks for Emergency Rescue

The unmanned aerial vehicle (UAV) network has gained significant attentions in recent years due to its various applications. However, the traffic security becomes the key threatening public safety issue in an emergency rescue system due to the increasing vulnerability of UAVs to cyber attacks in environments with high heterogeneities. Hence, in this paper, we propose a novel anomaly traffic detection architecture for UAV networks based on the software-defined networking (SDN) framework and blockchain technology. Specifically, SDN separates the control and data plane to enhance the network manageability and security. Meanwhile, the blockchain provides decentralized identity authentication and data security records. Besides, a complete security architecture requires an effective mechanism to detect the time-series based abnormal traffic. Thus, an integrated algorithm combining convolutional neural networks (CNNs) and Transformer (CNN+Transformer) for anomaly traffic detection is developed, which is called CTranATD. Finally, the simulation results show that the proposed CTranATD algorithm is effective and outperforms the individual CNN, Transformer, and LSTM algorithms for detecting anomaly traffic.CNN+Transformer Based Anomaly Traffic Detection in UAV Networks for Emergency RescueYulu Han, Ziye Jia, Sijie He, Nanjing University of Aeronautics and Astronautics; Yu Zhang, University of Newcastle; Qihui Wu, Nanjing University of Aeronautics and Astronautics

A UE-Initiated Handover Mechanism for Avoiding Disturbance on Extended Reality (XR) Servic...

Traditional handover mechanisms rely heavily on continuous user equipment (UE) measurements and frequent reporting to centralized gNBs. This approach introduces significant signaling overhead and latency, rendering it inadequate for latency-sensitive applications, such as extended reality (XR). This paper proposes a novel handover process that leverages geofencing and UE-based decision-making to improve handover performance. By introducing a geofencing approach, the UE remains in a measurement-free state within predefined regions, activating signal measurements only when exiting the geofence region. The UE independently evaluates the serving and neighbor gNBs and initiates a reverse handover request to the serving gNB, eliminating the need for periodic measurement reporting. Simulation results demonstrate that the proposed mechanism significantly reduces the number of measurements and signaling overhead, thereby improving scalability and resource efficiency.A UE-Initiated Handover Mechanism for Avoiding Disturbance on Extended Reality (XR) Services in 5G NetworksYu-An Shao, National Central University; Sheng-Shih Wang, Lunghwa University of Science and Technology; Shiann-Tsong Sheu, National Central University

A Channel Robust RFF Extraction Method Based on 802.11n HT-MF Preamble

In the research of Wi-Fi device identification, Radio Frequency Fingerprint (RFF) identification leverages the inherent hardware characteristics of devices to establish a unique identity at the physical layer. However, RFF identification is vulnerable to variations in the wireless channel. Although several studies have proposed channel-robust RFF extraction methods based on Wi-Fi signal preambles, these approaches rely on the legacy preamble of the 802.11 protocol, which results in relatively limited feature dimensions. This paper introduces the High Throughput Mixed Format (HT-MF) preamble under the 802.11n protocol framework, removing channel effects by calculating the ratio of three independent symbols in the frequency domain and subsequently extracting 24-dimensional RF fingerprint features. Maximum relevance minimum redundancy (MRMR) feature selection algorithm is then applied to remove redundant features and retain the most discriminative ones for the final RFF. This paper analytically shows that the three symbols in the HT-MF preamble exhibit similar channel response characteristics within the channel’s coherence time. We conducted extensive experiments on eight Wi-Fi devices across multiple channel environments, including four static and one dynamic scenario. Compared to methods without channel effect mitigation, our approach significantly improves channel robustness, achieving a 45.2% increase in average recognition accuracy. Additionally, when compared to other channel mitigation methods, our approach shows superior performance, with a maximum recognition accuracy improvement of 20.2%.A Channel Robust RFF Extraction Method Based on 802.11n HT-MF PreambleLong Li, Yuan Zhong, Fan Xiao, Xuan Yang, Dongming Li, Southeast University

Uniform Planar Array Based Weighted Cooperative Spectrum Sensing for Cognitive Radio Netwo...

Cooperative spectrum sensing (CSS) is essential for improving the spectrum efficiency and reliability of cognitive radio applications. Next-generation wireless communication networks increasingly employ uniform planar arrays (UPA) due to their ability to steer beamformers towards desired directions, mitigating interference and eavesdropping. However, the application of UPA-based CSS in cognitive radio remains largely unexplored. This paper proposes a multi-beam UPA-based weighted CSS (WCSS) framework to enhance detection reliability, applicable to various cognitive radio networks, including cellular, vehicular, and satellite communications. We first propose a weighting factor for commonly used energy detection (ED) and eigenvalue detection (EVD) techniques, based on the spatial variation of signal strengths resulting from UPA antenna beamforming. We then analytically characterize the performance of both weighted ED and weighted EVD by deriving closed-form expressions for false alarm and detection probabilities. Our numerical results, considering both static and dynamic user behaviors, demonstrate the superiority of WCSS in enhancing sensing performance compared to uniformly weighted detectors.Uniform Planar Array Based Weighted Cooperative Spectrum Sensing for Cognitive Radio NetworksCharith Dissanayake, Saman Atapattu, RMIT University; Prathapasinghe Dharmawansa, University of Oulu; Jing Fu, RMIT University; Sumei Sun, Institute for Infocomm Research; Sithamparanathan Kandeepan, RMIT Universitysikan

Pair-wise Hovering Location and Power Control for UAV-assisted NOMA-enabled Backscattering

As mobile networks increasingly support sustainable and green Internet of Things (IoT) applications, energy-efficient solutions that address coverage constraints have become paramount. Although backscatter communication (BSC) offers a low-power option for IoT devices, it can suffer from limited coverage. To overcome this, we leverage unmanned aerial vehicles (UAVs) and non-orthogonal multiple access (NOMA) to enhance both coverage and spectral efficiency. Motivated by vehicular communication applications, this paper investigates a NOMA-enabled UAV-assisted BSC framework to maximise system throughput by jointly optimising power allocation and trajectory scheduling. We derive a closed-form solution for the UAV’s optimal collection location and apply the Karush–Kuhn–Tucker (KKT) conditions to obtain the power allocation. The numerical and simulation results demonstrate sum-throughput improvements of 620.278% and 7.795% compared to two benchmark schemes, underscoring the potential of our approach for large-scale IoT deployments.Pair-wise Hovering Location and Power Control for UAV-assisted NOMA-enabled BackscatteringTianyi Zhang, University of New South Wales; Deepak Mishra, University of New South Wales (UNSW) Sydney; Jinhong Yuan, University of New South Wales; A. Seneviratne, UNSW Sydney

Joint Task Offloading and Resource Allocation in Vehicular Platoon Networks: A Federated R...

In the future, NR-V2X networks and platoon-based driving modes will become essential components of Intelligent Transportation Systems. However, with the advent of the Internet of Vehicles, the large-scale deployment of sensors and the explosive growth of data are driving the need for new solutions. Mobile edge computing has emerged as a key technology for addressing the distributed computing requirements. In this paper, we propose a Joint Optimization framework based on Federated multi-agent Reinforcement Learning (JOFRL) to solve the task offloading and resource allocation problems in a platoon-based NR-V2X network. Existing RL algorithms focus on either the communication link capacity or the completion rate of computing tasks. Differently, we consider the mutual influence between the allocation of computing and communication resources. We modify the reward function in the MARL framework so that each agent’s communication performance on V2V links is aligned with its computing performance. Our experimental results demonstrate that JOFRL outperforms other baseline algorithms. Specifically, JOFRL achieves improvements of 10.87%, 22.43% and 23.02% in computing and communication respectively compared with MADDPG, SAC and DDPG algorithm.Joint Task Offloading and Resource Allocation in Vehicular Platoon Networks: A Federated Reinforcement Learning ApproachTaomin Wang, Yiming Liu, Qiang Wang, Xuguang Cao, Jingyi Chen, Beijing University of Posts and Telecommunications