Vehicular Communications最新文献_第4页

SoCoMNNet: A SocioCognitive and memristive neural network-based context-aware GPS spoofing detection and mitigation in the Internet of drones SoCoMNNet：无人机互联网中基于社会认知和记忆神经网络的情境感知GPS欺骗检测和缓解

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-10-10 DOI: 10.1016/j.vehcom.2025.100980

Aiswarya S. Nair , Sabu M. Thampi , Jithu Vijay V. P.

GPS spoofing remains a significant and persistent threat to Internet of Drones (IoD), which compromises navigation integrity, security, and reliability. Drones, constrained by limited computational resources and power, demand innovative solutions to combat this easily exploitable vulnerability. Existing detection methods lack computational efficiency, contextual intelligence, and collaborative validation, leading to high false positives and low adaptability. In this paper, we propose a context-aware GPS spoofing detection and mitigation framework, SoCoMNNet, that integrates Memristive Neural Networks (MNNs) and a SocioCognitive fuzzy inference system for trust-driven behaviour analysis. The MNN module, deployed on each drone, detects navigation inconsistencies with minimal computational overhead, while the SocioCognitive system at the Ground Control Station (GCS) evaluates drone's behaviour in terms of Ability, Benevolence, and Integrity (ABI) to differentiate adversarial GPS spoofing from mission deviations. The predictions from the MNN and the behaviour assessment are combined using a weighted average, where both are given equal importance. In this way, the final result considers what the model predicts as well as how the drone is actually behaving, making GPS spoofing detection more accurate and context-aware. The contextual understanding provided by the SocioCognitive fuzzy system helps differentiate intentional deviations from unexpected ones, enhancing the overall resilience of the system. We have also developed a Kyber Post-Quantum Cryptography (PQC) secured GPS spoofing mitigation mechanism that helps drones to recover authentic GPS data during spoofing attacks. We evaluated the performance of MNN using MemTorch for memristor-based neural modelling, and NeuroSIM for hardware-level simulation and resource analysis. The fuzzy inference engine runs 27 rules and deduces five drone behaviours such as Discard, Unsatisfactory, Satisfactory, Reliable, and Ideal. Incorporating this context awareness into the detection process enables SoCoMNNet to reduce false positives during GPS spoofing detection. A statistical t-test was performed to show the impact of the proposed detection approach. The Kyber PQC mitigation approach was evaluated on Raspberry Pi 4 in terms of computation cost, communication overhead, and storage requirements. The results show reduced execution time, higher computational efficiency, lower memory usage, and stronger system security. Our integrated solution delivers a resilient and computationally efficient security framework for IoD in adversarial GPS spoofing environments.

GPS欺骗仍然是无人机互联网（IoD）的一个重大而持久的威胁，它损害了导航的完整性、安全性和可靠性。无人机受到有限的计算资源和能力的限制，需要创新的解决方案来对抗这种容易被利用的漏洞。现有检测方法缺乏计算效率、上下文智能和协同验证，导致误报率高、适应性低。在本文中，我们提出了一个上下文感知的GPS欺骗检测和缓解框架SoCoMNNet，它集成了记忆神经网络（MNNs）和社会认知模糊推理系统，用于信任驱动的行为分析。部署在每架无人机上的MNN模块，以最小的计算开销检测导航不一致，而地面控制站（GCS）的社会认知系统（social cognitive system）根据能力、仁慈和完整性（ABI）评估无人机的行为，以区分对抗性GPS欺骗和任务偏差。来自MNN的预测和行为评估使用加权平均值进行组合，其中两者具有同等的重要性。通过这种方式，最终结果考虑了模型预测的内容以及无人机的实际行为，使GPS欺骗检测更加准确和具有上下文感知能力。社会认知模糊系统提供的上下文理解有助于区分有意偏差和意外偏差，增强系统的整体弹性。我们还开发了Kyber后量子加密（PQC）安全的GPS欺骗缓解机制，帮助无人机在欺骗攻击期间恢复真实的GPS数据。我们使用MemTorch进行基于忆阻器的神经建模，使用NeuroSIM进行硬件级仿真和资源分析，评估了MNN的性能。模糊推理引擎运行27条规则，演绎出丢弃、不满意、满意、可靠、理想五种无人机行为。将这种上下文感知整合到检测过程中，SoCoMNNet可以减少GPS欺骗检测过程中的误报。进行统计t检验以显示所提出的检测方法的影响。Kyber PQC缓解方法在Raspberry Pi 4上进行了计算成本、通信开销和存储需求方面的评估。结果表明，减少了执行时间，提高了计算效率，降低了内存使用，增强了系统安全性。我们的集成解决方案为对抗GPS欺骗环境中的IoD提供了弹性和计算效率高的安全框架。

{"title":"SoCoMNNet: A SocioCognitive and memristive neural network-based context-aware GPS spoofing detection and mitigation in the Internet of drones","authors":"Aiswarya S. Nair , Sabu M. Thampi , Jithu Vijay V. P.","doi":"10.1016/j.vehcom.2025.100980","DOIUrl":"10.1016/j.vehcom.2025.100980","url":null,"abstract":"<div><div>GPS spoofing remains a significant and persistent threat to Internet of Drones (IoD), which compromises navigation integrity, security, and reliability. Drones, constrained by limited computational resources and power, demand innovative solutions to combat this easily exploitable vulnerability. Existing detection methods lack computational efficiency, contextual intelligence, and collaborative validation, leading to high false positives and low adaptability. In this paper, we propose a context-aware GPS spoofing detection and mitigation framework, SoCoMNNet, that integrates Memristive Neural Networks (MNNs) and a SocioCognitive fuzzy inference system for trust-driven behaviour analysis. The MNN module, deployed on each drone, detects navigation inconsistencies with minimal computational overhead, while the SocioCognitive system at the Ground Control Station (GCS) evaluates drone's behaviour in terms of Ability, Benevolence, and Integrity (ABI) to differentiate adversarial GPS spoofing from mission deviations. The predictions from the MNN and the behaviour assessment are combined using a weighted average, where both are given equal importance. In this way, the final result considers what the model predicts as well as how the drone is actually behaving, making GPS spoofing detection more accurate and context-aware. The contextual understanding provided by the SocioCognitive fuzzy system helps differentiate intentional deviations from unexpected ones, enhancing the overall resilience of the system. We have also developed a Kyber Post-Quantum Cryptography (PQC) secured GPS spoofing mitigation mechanism that helps drones to recover authentic GPS data during spoofing attacks. We evaluated the performance of MNN using MemTorch for memristor-based neural modelling, and NeuroSIM for hardware-level simulation and resource analysis. The fuzzy inference engine runs 27 rules and deduces five drone behaviours such as Discard, Unsatisfactory, Satisfactory, Reliable, and Ideal. Incorporating this context awareness into the detection process enables SoCoMNNet to reduce false positives during GPS spoofing detection. A statistical t-test was performed to show the impact of the proposed detection approach. The Kyber PQC mitigation approach was evaluated on Raspberry Pi 4 in terms of computation cost, communication overhead, and storage requirements. The results show reduced execution time, higher computational efficiency, lower memory usage, and stronger system security. Our integrated solution delivers a resilient and computationally efficient security framework for IoD in adversarial GPS spoofing environments.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"56 ","pages":"Article 100980"},"PeriodicalIF":6.5,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145321171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Resource allocation and model split for energy-efficient federated split learning in Internet of Vehicles with imperfect CSI 不完全CSI下车联网节能联合分割学习的资源分配与模型分割

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-10-10 DOI: 10.1016/j.vehcom.2025.100979

Youqiang Hu

Vehicular federated learning is able to deal with the data shortage dilemma in practical Artificial Intelligence (AI) projects in Internet of Vehicles (IoV) scenarios, but there is a bottleneck in this training paradigm, that is, the energy consumption issue. Since the training process is carried out on vehicles and the training tasks are generally computation-intensive, the battery lives of vehicles will be greatly affected if they participate in training. To improve the sustainability of the participants, split learning is introduced to the procedure of vehicular federated learning in this paper. Split learning divides the trained AI model into two parts. One is retained on terminals, and the other is sent to the cloud servers for remote training. Since the computation workload is reduced, the energy consumptions of participants are lowered. This training paradigm is called Vehicular Federated Split Learning (VFSL). Then, we model the computation and communication processes of VFSL and derive the energy consumption minimization problem. The estimated Channel State Information (CSI) between high-moving vehicles and Road Side Units (RSUs) is generally inaccurate. The imperfect CSI makes the formulated problem a stochastic mixed integer nonlinear programming problem, which is hard to solve. Therefore, we propose a resource allocation and model split strategy based on the Constrained Stochastic Successive Convex Approximation (CSSCA) and greedy algorithms. Simulation results demonstrate that the proposed strategy is able to achieve higher energy efficiency compared to the existing strategies in the case of imperfect CSI.

车辆联合学习能够解决车联网场景下实际人工智能（AI）项目中的数据短缺问题，但这种训练模式存在一个瓶颈，即能耗问题。由于训练过程是在车辆上进行的，训练任务通常是计算密集型的，因此如果车辆参加训练，将对其电池寿命产生很大影响。为了提高参与者的可持续性，本文将分裂学习引入到车辆联合学习过程中。拆分学习将训练好的AI模型分成两部分。一个保留在终端上，另一个发送到云服务器进行远程培训。由于减少了计算量，降低了参与者的能耗。这种训练范式被称为车辆联合分裂学习（VFSL）。然后，对VFSL的计算和通信过程进行建模，推导出能量消耗最小化问题。高速行驶车辆和路旁车辆之间的信道状态信息（CSI）估计通常是不准确的。不完善的CSI使得该问题成为一个难以求解的随机混合整数非线性规划问题。因此，我们提出了一种基于约束随机连续凸逼近（CSSCA）和贪心算法的资源分配和模型分割策略。仿真结果表明，在不完全CSI情况下，与现有策略相比，该策略能够实现更高的能效。

{"title":"Resource allocation and model split for energy-efficient federated split learning in Internet of Vehicles with imperfect CSI","authors":"Youqiang Hu","doi":"10.1016/j.vehcom.2025.100979","DOIUrl":"10.1016/j.vehcom.2025.100979","url":null,"abstract":"<div><div>Vehicular federated learning is able to deal with the data shortage dilemma in practical Artificial Intelligence (AI) projects in Internet of Vehicles (IoV) scenarios, but there is a bottleneck in this training paradigm, that is, the energy consumption issue. Since the training process is carried out on vehicles and the training tasks are generally computation-intensive, the battery lives of vehicles will be greatly affected if they participate in training. To improve the sustainability of the participants, split learning is introduced to the procedure of vehicular federated learning in this paper. Split learning divides the trained AI model into two parts. One is retained on terminals, and the other is sent to the cloud servers for remote training. Since the computation workload is reduced, the energy consumptions of participants are lowered. This training paradigm is called Vehicular Federated Split Learning (VFSL). Then, we model the computation and communication processes of VFSL and derive the energy consumption minimization problem. The estimated Channel State Information (CSI) between high-moving vehicles and Road Side Units (RSUs) is generally inaccurate. The imperfect CSI makes the formulated problem a stochastic mixed integer nonlinear programming problem, which is hard to solve. Therefore, we propose a resource allocation and model split strategy based on the Constrained Stochastic Successive Convex Approximation (CSSCA) and greedy algorithms. Simulation results demonstrate that the proposed strategy is able to achieve higher energy efficiency compared to the existing strategies in the case of imperfect CSI.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"56 ","pages":"Article 100979"},"PeriodicalIF":6.5,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145321169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Scalable AI-driven intent-based vehicle-to-everything communications for secure, low-latency, and energy-efficient smart cities 可扩展的人工智能驱动的基于意图的车辆到一切通信，用于安全、低延迟和节能的智能城市

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-10-09 DOI: 10.1016/j.vehcom.2025.100973

Wasim Ahmad , Farman Ali , Aitizaz Ali

The Internet of Things (IoT) and vehicle-to-vehicle (V2V) communication technologies are rapidly growing, and a smart, efficient, and scalable communication framework could accomplish the optimum resource allocation and network performance objective. In view of this, although significant progress has been made in terms of V2V communication through IoT, current urban deployments through dense traffic (> 1,500 vehicles / hour experience average packet latencies ≥120 ms and per-packet energy consumptions ≥100 J, precluding life critical safety applications. To address these constraints, we introduce a novel four-layer V2X framework, AI-integrated Intent-Based Networking (AI-IBN), that:

1.
Abstracts high-level safety and flow intents into the active per-link policies by way of a Deep Reinforcement-Learning controller.
2.
Integrates vehicle-to-vehicle(V2V)/vehicle-to-infrastructure (V2I)/vehicle-to-pedestrian (V2P)/vehicle-to-network (V2N) communication in a single intention manager.
3.
Formulates new subproblems that optimize intersection timing and allocate bus-lanes based, online, and with stochastic gradient updates; and
4.
Encrypts all intents in an end-to-end manner with a lightweight and symmetric-key authentication protocol.

In the urban traffic data set (2 km2 grid, 1500 veh / h) generated by Google Colab in Python, AI-IBN decreases the average packet latency from 150 to 50 ms (67%), reduces the energy per message from 150 to 50 J (67%) and increases the packet success rate from 0.65 to 0.93. In a specific intensity Jamming attack (we have disrupted 10% percent of the channel), our security module maintains a success rate of > 0.90, while a baseline is lower than 0.70. These results enable sub-50-ms and sub-50 J collision-avoidance alerts and set the stage for scalable, life-critical V2X safety services in integrated intelligent transport systems.

物联网（IoT）和车对车（V2V）通信技术正在快速发展，智能、高效、可扩展的通信框架可以实现最佳资源分配和网络性能目标。鉴于此，尽管在通过物联网实现V2V通信方面取得了重大进展，但目前在密集交通（1500辆/小时）的城市部署中，平均数据包延迟≥120ms，每数据包能耗≥100j，阻碍了生命关键安全应用。为了解决这些限制，我们引入了一种新的四层V2X框架，即ai集成的基于意图的网络（AI-IBN），即：1。通过深度强化学习控制器将高级安全和流意图抽象到主动的每链路策略中。将车对车(V2V)/车对基础设施(V2I)/车对行人(V2P)/车对网络（V2N）的通信集成在一个单一的意图管理器中。提出了基于随机梯度更新、在线优化交叉口时间和公交车道分配的新子问题；and4。使用轻量级和对称密钥身份验证协议以端到端方式加密所有意图。在Python中的谷歌Colab生成的城市交通数据集（2 km2网格，1500 veh / h）中，AI-IBN将平均数据包延迟从150 ms降低到50 ms(67%)，将每条消息的能量从150 J降低到50 J(67%)，并将数据包成功率从0.65提高到0.93。在特定强度的干扰攻击中（我们已经干扰了10%的信道），我们的安全模块保持了0.90的成功率，而基线低于0.70。这些结果可实现低于50ms和50j的碰撞避免警报，并为集成智能交通系统中可扩展的、关键生命的V2X安全服务奠定了基础。

{"title":"Scalable AI-driven intent-based vehicle-to-everything communications for secure, low-latency, and energy-efficient smart cities","authors":"Wasim Ahmad , Farman Ali , Aitizaz Ali","doi":"10.1016/j.vehcom.2025.100973","DOIUrl":"10.1016/j.vehcom.2025.100973","url":null,"abstract":"<div><div>The Internet of Things (IoT) and vehicle-to-vehicle (V2V) communication technologies are rapidly growing, and a smart, efficient, and scalable communication framework could accomplish the optimum resource allocation and network performance objective. In view of this, although significant progress has been made in terms of V2V communication through IoT, current urban deployments through dense traffic (> 1,500 vehicles / hour experience average packet latencies ≥120 ms and per-packet energy consumptions ≥100 J, precluding life critical safety applications. To address these constraints, we introduce a novel four-layer V2X framework, AI-integrated Intent-Based Networking (AI-IBN), that:<ul><li><span>1.</span><span><div>Abstracts high-level safety and flow intents into the active per-link policies by way of a Deep Reinforcement-Learning controller.</div></span></li><li><span>2.</span><span><div>Integrates vehicle-to-vehicle(V2V)/vehicle-to-infrastructure (V2I)/vehicle-to-pedestrian (V2P)/vehicle-to-network (V2N) communication in a single intention manager.</div></span></li><li><span>3.</span><span><div>Formulates new subproblems that optimize intersection timing and allocate bus-lanes based, online, and with stochastic gradient updates; and</div></span></li><li><span>4.</span><span><div>Encrypts all intents in an end-to-end manner with a lightweight and symmetric-key authentication protocol.</div></span></li></ul> In the urban traffic data set (2 km2 grid, 1500 veh / h) generated by Google Colab in Python, AI-IBN decreases the average packet latency from 150 to 50 ms (67%), reduces the energy per message from 150 to 50 J (67%) and increases the packet success rate from 0.65 to 0.93. In a specific intensity Jamming attack (we have disrupted 10% percent of the channel), our security module maintains a success rate of > 0.90, while a baseline is lower than 0.70. These results enable sub-50-ms and sub-50 J collision-avoidance alerts and set the stage for scalable, life-critical V2X safety services in integrated intelligent transport systems.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"56 ","pages":"Article 100973"},"PeriodicalIF":6.5,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145268473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of multichannel operation mechanisms for vehicular networks 车辆网络多通道运行机制评价

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-10-07 DOI: 10.1016/j.vehcom.2025.100978

Felipe García Vidal, Esteban Egea López, José Santa Lozano

Upon the massive deployment of Cooperative Intelligent Transportation Systems (C-ITS), services developed for connected vehicles need an efficient, reliable and predictable network access to assure proper operation. European Telecommunications Standards Institute (ETSI) Release 2 services cannot be deployed using a single control channel, and require the management of multiple channels used simultaneously by applications. Because of this, ETSI defined a mechanism called Multi-Channel Operation (MCO). Two simple MCO load allocation mechanisms have been recommended, load balancing and sequential filling, but they have not been evaluated in detail until now. In this paper, these two mechanisms, as well as their congestion control variants, are evaluated. An open-source simulation framework has been implemented for such a work, which is open to future extensions. Then, through multiple evaluations following the ETSI simulation setup, we discuss the behavior of these mechanisms under scenarios with a highly congested medium, employing different traffic loads and vehicular densities. Our results show that MCO improvement is limited under high-load conditions, by saturation of channels before switching to a new one (sequential filling) and synchronization of channel assignment among vehicles (load balancing), and the introduction of a simple reactive congestion control does not improve their performance. The main limitations are examined, and recommendations are provided to guide the evolution of these mechanisms.

随着协作式智能交通系统（C-ITS）的大规模部署，为联网车辆开发的服务需要一个高效、可靠和可预测的网络接入，以确保正常运行。欧洲电信标准协会（ETSI）第2版业务不能使用单个控制通道进行部署，而需要管理应用程序同时使用的多个通道。因此，ETSI定义了一种称为多通道操作（MCO）的机制。推荐了两种简单的MCO负载分配机制：负载平衡和顺序填充，但直到现在还没有对它们进行详细的评估。本文对这两种机制及其拥塞控制变体进行了评估。已经为这样的工作实现了一个开源模拟框架，它对未来的扩展是开放的。然后，通过ETSI模拟设置后的多次评估，我们讨论了这些机制在使用不同交通负载和车辆密度的高度拥挤介质下的行为。我们的研究结果表明，在高负载条件下，由于通道在切换到新通道之前已经饱和（顺序填充）和车辆之间通道分配的同步（负载平衡），MCO的改进是有限的，并且引入简单的反应性拥塞控制并不能提高它们的性能。研究了主要的局限性，并提出了指导这些机制发展的建议。

{"title":"Evaluation of multichannel operation mechanisms for vehicular networks","authors":"Felipe García Vidal, Esteban Egea López, José Santa Lozano","doi":"10.1016/j.vehcom.2025.100978","DOIUrl":"10.1016/j.vehcom.2025.100978","url":null,"abstract":"<div><div>Upon the massive deployment of Cooperative Intelligent Transportation Systems (C-ITS), services developed for connected vehicles need an efficient, reliable and predictable network access to assure proper operation. European Telecommunications Standards Institute (ETSI) Release 2 services cannot be deployed using a single control channel, and require the management of multiple channels used simultaneously by applications. Because of this, ETSI defined a mechanism called Multi-Channel Operation (MCO). Two simple MCO load allocation mechanisms have been recommended, load balancing and sequential filling, but they have not been evaluated in detail until now. In this paper, these two mechanisms, as well as their congestion control variants, are evaluated. An open-source simulation framework has been implemented for such a work, which is open to future extensions. Then, through multiple evaluations following the ETSI simulation setup, we discuss the behavior of these mechanisms under scenarios with a highly congested medium, employing different traffic loads and vehicular densities. Our results show that MCO improvement is limited under high-load conditions, by saturation of channels before switching to a new one (sequential filling) and synchronization of channel assignment among vehicles (load balancing), and the introduction of a simple reactive congestion control does not improve their performance. The main limitations are examined, and recommendations are provided to guide the evolution of these mechanisms.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"56 ","pages":"Article 100978"},"PeriodicalIF":6.5,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145268475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A privacy-enhanced authentication scheme for VANETs based on blockchain and zero-knowledge proof 一种基于区块链和零知识证明的vanet隐私增强认证方案

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-10-03 DOI: 10.1016/j.vehcom.2025.100976

Shangping Wang , Qi Huang, Ruoxin Yan, Juanjuan Ma, Xiaoling Xie

The rapid development of Intelligent Transportation Systems (ITS) and autonomous driving technologies has made secure authentication and privacy protection of vehicle identities in Vehicular Ad Hoc Networks (VANETs) a hot research issue. Existing solutions typically rely on pseudonym-based approaches. These approaches incur large storage overhead and computational costs, which limit their scalability and efficiency. To address this problem, this paper proposes a novel anonymous authentication scheme in VANETs that synergistically integrates zero-knowledge proof (ZKP) and blockchain technology. An identity-based polynomial commitment is used in the present scheme to achieve privacy-preserving authentication, which ensures the anonymity of the vehicle without revealing sensitive information. Additionally, an identity-based signature algorithm, based on the Gap Diffie-Hellman (GDH) problem, ensures session unlinkability, enhancing connection security. Incorporating the Merkle Patricia Trie (MPT) into the blockchain framework optimizes data retrieval efficiency while minimizing storage and computational burdens on the central server. Blockchain's inherent immutability and transparency further enhance data integrity and security.

随着智能交通系统（ITS）和自动驾驶技术的快速发展，车辆自组织网络（VANETs）中车辆身份的安全认证和隐私保护成为研究热点。现有的解决方案通常依赖于基于假名的方法。这些方法会产生大量的存储开销和计算成本，从而限制了它们的可伸缩性和效率。为了解决这一问题，本文提出了一种新的VANETs匿名认证方案，该方案协同集成了零知识证明（ZKP）和区块链技术。该方案采用基于身份的多项式承诺来实现保护隐私的身份验证，保证了车辆的匿名性而不泄露敏感信息。另外，基于Gap Diffie-Hellman （GDH）问题的身份签名算法保证了会话的不可链接性，提高了连接的安全性。将Merkle Patricia Trie （MPT）合并到区块链框架中可以优化数据检索效率，同时最大限度地减少中央服务器上的存储和计算负担。区块链固有的不变性和透明性进一步增强了数据的完整性和安全性。

{"title":"A privacy-enhanced authentication scheme for VANETs based on blockchain and zero-knowledge proof","authors":"Shangping Wang , Qi Huang, Ruoxin Yan, Juanjuan Ma, Xiaoling Xie","doi":"10.1016/j.vehcom.2025.100976","DOIUrl":"10.1016/j.vehcom.2025.100976","url":null,"abstract":"<div><div>The rapid development of Intelligent Transportation Systems (ITS) and autonomous driving technologies has made secure authentication and privacy protection of vehicle identities in Vehicular Ad Hoc Networks (VANETs) a hot research issue. Existing solutions typically rely on pseudonym-based approaches. These approaches incur large storage overhead and computational costs, which limit their scalability and efficiency. To address this problem, this paper proposes a novel anonymous authentication scheme in VANETs that synergistically integrates zero-knowledge proof (ZKP) and blockchain technology. An identity-based polynomial commitment is used in the present scheme to achieve privacy-preserving authentication, which ensures the anonymity of the vehicle without revealing sensitive information. Additionally, an identity-based signature algorithm, based on the Gap Diffie-Hellman (GDH) problem, ensures session unlinkability, enhancing connection security. Incorporating the Merkle Patricia Trie (MPT) into the blockchain framework optimizes data retrieval efficiency while minimizing storage and computational burdens on the central server. Blockchain's inherent immutability and transparency further enhance data integrity and security.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"56 ","pages":"Article 100976"},"PeriodicalIF":6.5,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145268464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

UAV-assisted wireless communications in the 6G-and-beyond era: An extensive survey on characteristics, standardization and regulations, enabling technologies, challenges, and future directions 6g及以上时代的无人机辅助无线通信：对特征、标准化和法规、使能技术、挑战和未来方向的广泛调查

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-10-01 DOI: 10.1016/j.vehcom.2025.100977

Mobasshir Mahbub , Mir Md. Saym , Sarwar Jahan , Anup Kumar Paul , Alireza Vahid , Seyyedali Hosseinalipour , Bobby Barua , Hen-Geul Yeh , Raed M. Shubair , Tarik Taleb , Aryan Kaushik , Mohammed H. Alsharif , M. Shariful Islam , Russel Reza Mahmud , Dusit Niyato

Unmanned Aerial Vehicles (UAVs) have emerged as transformative tools in wireless communication systems, revolutionizing the landscape of next-generation networks, including 6G and beyond. This survey comprehensively examines the technical advancements, challenges, and future directions of UAV-assisted wireless communications. It begins with analyzing UAV characteristics, such as flight dynamics, payload capacity, and power systems, and explores their pivotal role in enabling efficient connectivity across terrestrial, aerial, and maritime domains. The survey then delves into enabling technologies like advanced antenna designs, beamforming techniques, channel modeling, energy consumption models, and mobility optimization, emphasizing their necessity for achieving seamless UAV-to-ground, UAV-to-UAV, and UAV-to-satellite interactions. It further discusses regulatory frameworks and standardization efforts by global entities to address safety, spectrum allocation, and privacy concerns. Innovative routing protocols, including AI-driven and software-defined networking approaches, are analyzed, highlighting their potential to enhance scalability, reduce latency, and optimize resource management in dynamic UAV networks. This work identifies significant challenges such as energy efficiency, secure communication in hostile environments, and trajectory optimization while navigating complex three-dimensional (3D) spaces. The survey finally proposes directions for future research, including the exploration of sub-THz and THz communication, cross-layer routing, and the integration of UAVs with emerging networking paradigms. By synthesizing lessons learned and outlining unresolved questions, this paper serves as a resource for advancing UAV-enabled connectivity and unlocking new capabilities for ubiquitous and resilient wireless networks.

无人驾驶飞行器（uav）已经成为无线通信系统中的变革性工具，彻底改变了下一代网络的格局，包括6G及以后。这项调查全面考察了无人机辅助无线通信的技术进步、挑战和未来方向。它首先分析无人机的特性，如飞行动力学、有效载荷能力和动力系统，并探索它们在实现陆地、空中和海洋领域的有效连接方面的关键作用。然后，调查深入研究了先进的天线设计、波束成形技术、信道建模、能耗模型和机动性优化等使能技术，强调了实现无人机对地、无人机对无人机以及无人机对卫星无缝交互的必要性。它进一步讨论了全球实体为解决安全、频谱分配和隐私问题而开展的监管框架和标准化工作。分析了创新的路由协议，包括人工智能驱动和软件定义的网络方法，强调了它们在动态无人机网络中增强可扩展性、减少延迟和优化资源管理方面的潜力。这项工作确定了重大挑战，如能源效率、恶劣环境下的安全通信以及导航复杂三维空间时的轨迹优化。调查最后提出了未来的研究方向，包括探索亚太赫兹和太赫兹通信，跨层路由以及无人机与新兴网络范式的集成。通过综合经验教训和概述未解决的问题，本文可以作为推进无人机连接和释放无处不在的弹性无线网络新功能的资源。

{"title":"UAV-assisted wireless communications in the 6G-and-beyond era: An extensive survey on characteristics, standardization and regulations, enabling technologies, challenges, and future directions","authors":"Mobasshir Mahbub , Mir Md. Saym , Sarwar Jahan , Anup Kumar Paul , Alireza Vahid , Seyyedali Hosseinalipour , Bobby Barua , Hen-Geul Yeh , Raed M. Shubair , Tarik Taleb , Aryan Kaushik , Mohammed H. Alsharif , M. Shariful Islam , Russel Reza Mahmud , Dusit Niyato","doi":"10.1016/j.vehcom.2025.100977","DOIUrl":"10.1016/j.vehcom.2025.100977","url":null,"abstract":"<div><div>Unmanned Aerial Vehicles (UAVs) have emerged as transformative tools in wireless communication systems, revolutionizing the landscape of next-generation networks, including 6G and beyond. This survey comprehensively examines the technical advancements, challenges, and future directions of UAV-assisted wireless communications. It begins with analyzing UAV characteristics, such as flight dynamics, payload capacity, and power systems, and explores their pivotal role in enabling efficient connectivity across terrestrial, aerial, and maritime domains. The survey then delves into enabling technologies like advanced antenna designs, beamforming techniques, channel modeling, energy consumption models, and mobility optimization, emphasizing their necessity for achieving seamless UAV-to-ground, UAV-to-UAV, and UAV-to-satellite interactions. It further discusses regulatory frameworks and standardization efforts by global entities to address safety, spectrum allocation, and privacy concerns. Innovative routing protocols, including AI-driven and software-defined networking approaches, are analyzed, highlighting their potential to enhance scalability, reduce latency, and optimize resource management in dynamic UAV networks. This work identifies significant challenges such as energy efficiency, secure communication in hostile environments, and trajectory optimization while navigating complex three-dimensional (3D) spaces. The survey finally proposes directions for future research, including the exploration of sub-THz and THz communication, cross-layer routing, and the integration of UAVs with emerging networking paradigms. By synthesizing lessons learned and outlining unresolved questions, this paper serves as a resource for advancing UAV-enabled connectivity and unlocking new capabilities for ubiquitous and resilient wireless networks.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"56 ","pages":"Article 100977"},"PeriodicalIF":6.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145268474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing road side units connectivity in intelligent transportation systems with optical network solutions 利用光网络解决方案优化智能交通系统中道路侧单元的连接

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-09-29 DOI: 10.1016/j.vehcom.2025.100975

Camilo Anzola-Rojas, Ignacio de Miguel, Noemí Merayo, Juan Carlos Aguado, Rubén M. Lorenzo, Ramón J. Durán Barroso

A fundamental component of Intelligent Transportation Systems (ITS) is connectivity. For connected vehicles to be aware of events occurring nearby, or even far from them, roadside infrastructure is essential. Roadside Units (RSUs) are electronic equipment placed along highways to provide connectivity and share data with vehicles, other RSUs, and networks. Connected vehicles require wireless communication with RSUs; however, depending on the complexity of tasks and the number of users, spectrum resources may be insufficient to handle all required communication between vehicles, RSUs and external networks. Since RSUs are stationary, optical fiber is an ideal technology for interconnecting them and linking them to the Internet and the cloud, providing reliable, high-performance connectivity, with low signal attenuation and high bandwidth. This paper proposes a model for deploying fiber networks to connect RSUs, with a focus on minimizing capital expenditures, including costs for civil works, cables, and devices, which are critical considerations given the large distances involved. Specifically, we consider and compare two established optical network technologies: point-to-point (PtP) and passive optical networks (PON). To support this comparison, we present and test two novel Integer Linear Programming (ILP) formulations: one for PtP and one for PON. Additionally, we introduce a genetic algorithm that improves upon a previously proposed heuristic, achieving near-optimal results comparable to the ILP formulation, while efficiently solving large-scale scenarios. The results show that the optimal choice between PtP and PON depends on the deployment area and density of RSUs.

智能交通系统（ITS）的一个基本组成部分是连通性。为了让联网车辆了解附近甚至远处发生的事件，路边基础设施是必不可少的。路边单元（rsu）是放置在高速公路沿线的电子设备，用于与车辆、其他路边单元和网络提供连接和共享数据。联网车辆需要与rsu进行无线通信；然而，根据任务的复杂性和用户的数量，频谱资源可能不足以处理车辆、rsu和外部网络之间所需的所有通信。由于rsu是固定的，因此光纤是将它们互连并连接到互联网和云的理想技术，提供可靠、高性能的连接，具有低信号衰减和高带宽。本文提出了一个部署光纤网络连接rsu的模型，重点是最小化资本支出，包括土建工程、电缆和设备的成本，这是考虑到所涉及的大距离的关键考虑因素。具体来说，我们考虑并比较了两种已建立的光网络技术：点对点（PtP）和无源光网络（PON）。为了支持这种比较，我们提出并测试了两个新的整数线性规划（ILP）公式：一个用于PtP，一个用于PON。此外，我们引入了一种遗传算法，该算法改进了先前提出的启发式算法，实现了与ILP公式相当的接近最优结果，同时有效地解决了大规模场景。结果表明，PtP和PON的最优选择取决于rsu的部署面积和密度。

{"title":"Optimizing road side units connectivity in intelligent transportation systems with optical network solutions","authors":"Camilo Anzola-Rojas, Ignacio de Miguel, Noemí Merayo, Juan Carlos Aguado, Rubén M. Lorenzo, Ramón J. Durán Barroso","doi":"10.1016/j.vehcom.2025.100975","DOIUrl":"10.1016/j.vehcom.2025.100975","url":null,"abstract":"<div><div>A fundamental component of Intelligent Transportation Systems (ITS) is connectivity. For connected vehicles to be aware of events occurring nearby, or even far from them, roadside infrastructure is essential. Roadside Units (RSUs) are electronic equipment placed along highways to provide connectivity and share data with vehicles, other RSUs, and networks. Connected vehicles require wireless communication with RSUs; however, depending on the complexity of tasks and the number of users, spectrum resources may be insufficient to handle all required communication between vehicles, RSUs and external networks. Since RSUs are stationary, optical fiber is an ideal technology for interconnecting them and linking them to the Internet and the cloud, providing reliable, high-performance connectivity, with low signal attenuation and high bandwidth. This paper proposes a model for deploying fiber networks to connect RSUs, with a focus on minimizing capital expenditures, including costs for civil works, cables, and devices, which are critical considerations given the large distances involved. Specifically, we consider and compare two established optical network technologies: point-to-point (PtP) and passive optical networks (PON). To support this comparison, we present and test two novel Integer Linear Programming (ILP) formulations: one for PtP and one for PON. Additionally, we introduce a genetic algorithm that improves upon a previously proposed heuristic, achieving near-optimal results comparable to the ILP formulation, while efficiently solving large-scale scenarios. The results show that the optimal choice between PtP and PON depends on the deployment area and density of RSUs.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"56 ","pages":"Article 100975"},"PeriodicalIF":6.5,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Distributed Dynamic Consensus (DDC) protocol for multi-UAV 3D trajectory planning and resource allocation 多无人机三维轨迹规划与资源分配的分布式动态共识协议

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-09-17 DOI: 10.1016/j.vehcom.2025.100969

Tayyaba Khurshid , Waqas Ahmed , Rizwan Ahmad , Muhammad Mahtab Alam , Joel J.P.C. Rodrigues

In a Multiple Unmanned Air Vehicle (m-UAV) system, employing a centralized communication approach poses many challenges such as communication range limitations, energy efficiency, latency, etc. due to limited UAV resources. On the other hand, a distributed consensus approach has the ability to overcome these limitations and possesses numerous advantages if appropriate coordination mechanism among the UAVs is employed. Therefore, in this paper, we investigate joint optimization of 3D trajectory and UAV resources using a distributed consensus approach. We assume that User Devices (UDs) compute a portion of the task locally and offload the remaining part to the nearby Mobile Edge Computing (MEC) based UAV. Considering UAV dynamics and environmental constraints, a Deep Deterministic Policy Gradient (DDPG) is presented based on Distributed Dynamic Consensus (DDC) approach that utilizes consensus theory for distributed computing. We classified DDC into three cases namely; Distributed Velocity Consensus (DVC), Distributed Error Consensus (DEC), and Distributed Dynamic Velocity Consensus (DDVC). The performance of all three cases based on cost percentage (cost is the sum of normalized time delay and normalized energy consumption) and observed that DEC achieves minimum cost i.e., 40.62 whereas DVC and DDVC settled at 48.18 and 44.06 respectively. We further investigate the performance of DEC in partially connected, moderately connected, and fully connected networks. With centralized and autonomous decision-making scenario as a benchmark, results show that the DEC in the partially connected scenario converges faster with a lower cost.

在多架无人机（m-UAV）系统中，由于无人机资源有限，采用集中式通信方式存在通信距离限制、能源效率、延迟等诸多挑战。另一方面，如果采用适当的无人机间协调机制，分布式共识方法能够克服这些局限性，并具有许多优点。因此，本文采用分布式共识方法研究了三维轨迹和无人机资源的联合优化问题。我们假设用户设备（UDs）在本地计算任务的一部分，并将其余部分卸载给附近基于移动边缘计算（MEC）的无人机。考虑无人机的动力学和环境约束，提出了一种基于分布式动态共识（DDC）的深度确定性策略梯度（DDPG）方法，该方法将共识理论应用于分布式计算。我们将DDC分为三种情况：分布式速度一致（DVC）、分布式误差一致（DEC）和分布式动态速度一致（DDVC）。基于成本百分比（成本为归一化时延和归一化能耗之和）对三种情况进行性能分析，发现DEC的成本最小，为40.62，而DVC和DDVC的成本分别为48.18和44.06。我们进一步研究了DEC在部分连接、中等连接和完全连接网络中的性能。以集中式自主决策场景为基准，结果表明，部分连接场景下的DEC收敛速度更快，成本更低。

{"title":"Distributed Dynamic Consensus (DDC) protocol for multi-UAV 3D trajectory planning and resource allocation","authors":"Tayyaba Khurshid , Waqas Ahmed , Rizwan Ahmad , Muhammad Mahtab Alam , Joel J.P.C. Rodrigues","doi":"10.1016/j.vehcom.2025.100969","DOIUrl":"10.1016/j.vehcom.2025.100969","url":null,"abstract":"<div><div>In a Multiple Unmanned Air Vehicle (m-UAV) system, employing a centralized communication approach poses many challenges such as communication range limitations, energy efficiency, latency, etc. due to limited UAV resources. On the other hand, a distributed consensus approach has the ability to overcome these limitations and possesses numerous advantages if appropriate coordination mechanism among the UAVs is employed. Therefore, in this paper, we investigate joint optimization of 3D trajectory and UAV resources using a distributed consensus approach. We assume that User Devices (UDs) compute a portion of the task locally and offload the remaining part to the nearby Mobile Edge Computing (MEC) based UAV. Considering UAV dynamics and environmental constraints, a Deep Deterministic Policy Gradient (DDPG) is presented based on Distributed Dynamic Consensus (DDC) approach that utilizes consensus theory for distributed computing. We classified DDC into three cases namely; Distributed Velocity Consensus (DVC), Distributed Error Consensus (DEC), and Distributed Dynamic Velocity Consensus (DDVC). The performance of all three cases based on cost percentage (cost is the sum of normalized time delay and normalized energy consumption) and observed that DEC achieves minimum cost i.e., 40.62 whereas DVC and DDVC settled at 48.18 and 44.06 respectively. We further investigate the performance of DEC in partially connected, moderately connected, and fully connected networks. With centralized and autonomous decision-making scenario as a benchmark, results show that the DEC in the partially connected scenario converges faster with a lower cost.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"56 ","pages":"Article 100969"},"PeriodicalIF":6.5,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SHAP-based feature selection and MASV-weighted SMOTE for enhanced attack detection in VANETs 基于shap的特征选择和masv加权SMOTE在vanet中的增强攻击检测

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-09-17 DOI: 10.1016/j.vehcom.2025.100970

Zawiyah Saharuna , Tohari Ahmad , Royyana Muslim Ijtihadie

Vehicular Ad Hoc Networks (VANETs) are integral to Intelligent Transportation Systems (ITS) but remain highly vulnerable to cyberattacks, such as malicious attacks and position falsification. Detection is hindered by high-dimensional traffic data and severe class imbalance. Existing intrusion detection methods often overlook feature importance, limiting adaptability to different attack types. This study proposes an adaptive Intrusion Detection System (IDS) integrating SHAP-based feature selection with a MASV-weighted SMOTE technique. To the best of our knowledge, this is the first framework to leverage SHAP values not only for feature selection but also to guide class rebalancing during synthetic sample generation. Unlike conventional approaches, which treat all features equally, our method prioritizes features based on their Mean Absolute SHAP Values (MASV) in both selection and oversampling. Evaluated on CICIDS-2017 and validated on VeReMi, the framework demonstrates strong generalizability between datasets. It reduces feature dimensionality by up to 80% (78 to 15 features) while maintaining 99.91% accuracy, achieving up to 50.79% faster training and real-time inference below 0.1 ms per instance. MASV-weighted SMOTE transforms minority class detection performance, elevating the Infiltration attack F1-score from 0 to 88.89% and PR-AUC from 4.43% to 100%. These results outperform baseline models, enabling accurate, efficient, and interpretable IDS for VANETs security applications.

车辆自组织网络（VANETs）是智能交通系统（ITS）不可或缺的一部分，但仍然极易受到网络攻击，例如恶意攻击和位置伪造。高维的交通数据和严重的类不平衡阻碍了检测。现有的入侵检测方法往往忽略了特征的重要性，限制了对不同攻击类型的适应性。本研究提出一种结合基于shap的特征选择与masv加权SMOTE技术的自适应入侵检测系统（IDS）。据我们所知，这是第一个不仅利用SHAP值进行特征选择，而且还在合成样本生成过程中指导类再平衡的框架。与同等对待所有特征的传统方法不同，我们的方法在选择和过采样中基于特征的Mean Absolute shav （MASV）来确定特征的优先级。在CICIDS-2017上进行了评估，并在VeReMi上进行了验证，结果表明该框架在数据集之间具有很强的通用性。它将特征维度降低了80%（78到15个特征），同时保持了99.91%的准确率，实现了高达50.79%的训练速度和每实例0.1毫秒以下的实时推理。masv加权SMOTE改变了少数类检测性能，将渗透攻击的f1得分从0提高到88.89%，PR-AUC从4.43%提高到100%。这些结果优于基线模型，为VANETs安全应用程序提供准确、高效和可解释的IDS。

{"title":"SHAP-based feature selection and MASV-weighted SMOTE for enhanced attack detection in VANETs","authors":"Zawiyah Saharuna , Tohari Ahmad , Royyana Muslim Ijtihadie","doi":"10.1016/j.vehcom.2025.100970","DOIUrl":"10.1016/j.vehcom.2025.100970","url":null,"abstract":"<div><div>Vehicular Ad Hoc Networks (VANETs) are integral to Intelligent Transportation Systems (ITS) but remain highly vulnerable to cyberattacks, such as malicious attacks and position falsification. Detection is hindered by high-dimensional traffic data and severe class imbalance. Existing intrusion detection methods often overlook feature importance, limiting adaptability to different attack types. This study proposes an adaptive Intrusion Detection System (IDS) integrating SHAP-based feature selection with a MASV-weighted SMOTE technique. To the best of our knowledge, this is the first framework to leverage SHAP values not only for feature selection but also to guide class rebalancing during synthetic sample generation. Unlike conventional approaches, which treat all features equally, our method prioritizes features based on their Mean Absolute SHAP Values (MASV) in both selection and oversampling. Evaluated on CICIDS-2017 and validated on VeReMi, the framework demonstrates strong generalizability between datasets. It reduces feature dimensionality by up to 80% (78 to 15 features) while maintaining 99.91% accuracy, achieving up to 50.79% faster training and real-time inference below 0.1 ms per instance. MASV-weighted SMOTE transforms minority class detection performance, elevating the Infiltration attack F1-score from 0 to 88.89% and PR-AUC from 4.43% to 100%. These results outperform baseline models, enabling accurate, efficient, and interpretable IDS for VANETs security applications.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"56 ","pages":"Article 100970"},"PeriodicalIF":6.5,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145121225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FANET-enabled cluster-based emergency communication with 3D mobility in 5G and beyond 支持fanet的基于集群的应急通信，具有5G及以后的3D移动性

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-09-17 DOI: 10.1016/j.vehcom.2025.100971

Md. Thouhidur Rahman , A.F.M. Shahen Shah , Muhammet Ali Karabulut , Haci Ilhan

In 5G and beyond, unmanned aerial vehicles (UAVs) are highly valued for their communication capabilities, affordability, and deployment flexibility. Multi-UAV systems, which operate in ad-hoc networks known as UAV ad-hoc networks or flying ad-hoc networks (FANETs), represent some of the most promising technologies both currently and in the future. In disaster situations, it will be crucial to set up temporary UAV-based emergency flying base stations (BSs), provide wireless coverage in cellular networks, and establish communication relays for long-distance data transmission. To establish this network, efficient communication between the UAVs is the most vital point. Additionally, due to mobility, the topology changes frequently, leading to potential collisions and packet losses. Therefore, in this paper, a minimum distance clustering scheme (MDCS)-based FANET is proposed, where the topology is controlled by a back-off mechanism and network connectivity is maintained even when the UAVs are moving at different altitudes by calculating the relative velocity on a 3D platform while considering the randomized path-based 3D mobility model. An efficient cluster build-up process and a method for determining the position of the cluster head (CH) are introduced to control the cluster proficiently. An analytical study is performed considering Rayleigh, Nakagami-m, and Rician fading channels. Moreover, the obtained Monte Carlo simulation results justify the analytical findings. Finally, the simulations show better results than existing work in terms of throughput with changes in distance, velocity, and the number of UAVs, as well as outage probability, packet dropping rate, and delay. In the case of the Rician fading channel, for 40 UAVs, a cluster size of 7 or fewer is more favorable, showing a maximum connection distance of 165 m, a maximum throughput of 10.2 Mbps, and a maximum delay of 55.57 ms.

在5G及以后，无人驾驶飞行器（uav）因其通信能力、可负担性和部署灵活性而受到高度重视。多无人机系统，在称为无人机自组织网络或飞行自组织网络（fanet）的自组织网络中操作，代表了当前和未来最有前途的一些技术。在灾害情况下，建立基于无人机的临时应急飞行基站（BSs），在蜂窝网络中提供无线覆盖，建立远程数据传输的通信中继将是至关重要的。要建立这一网络，无人机之间的有效通信是最关键的一点。此外，由于移动性，拓扑结构经常变化，导致潜在的冲突和丢包。为此，本文提出了一种基于最小距离聚类方案（MDCS）的FANET，该方案在考虑基于随机路径的三维机动性模型的基础上，通过计算无人机在三维平台上的相对速度，通过后退机制控制拓扑结构，使无人机在不同高度移动时也能保持网络连通性。介绍了一种有效的簇建立过程和确定簇头（CH）位置的方法，以熟练地控制簇。对Rayleigh、Nakagami-m和rici衰落信道进行了分析研究。此外，得到的蒙特卡罗模拟结果验证了分析结果。最后，在距离、速度、无人机数量变化的吞吐量、中断概率、丢包率和延迟方面，仿真结果优于现有工作。在专家衰落信道的情况下，对于40架无人机，集群大小为7或更少更有利，显示最大连接距离为165米，最大吞吐量为10.2 Mbps，最大延迟为55.57 ms。

{"title":"FANET-enabled cluster-based emergency communication with 3D mobility in 5G and beyond","authors":"Md. Thouhidur Rahman , A.F.M. Shahen Shah , Muhammet Ali Karabulut , Haci Ilhan","doi":"10.1016/j.vehcom.2025.100971","DOIUrl":"10.1016/j.vehcom.2025.100971","url":null,"abstract":"<div><div>In 5G and beyond, unmanned aerial vehicles (UAVs) are highly valued for their communication capabilities, affordability, and deployment flexibility. Multi-UAV systems, which operate in ad-hoc networks known as UAV ad-hoc networks or flying ad-hoc networks (FANETs), represent some of the most promising technologies both currently and in the future. In disaster situations, it will be crucial to set up temporary UAV-based emergency flying base stations (BSs), provide wireless coverage in cellular networks, and establish communication relays for long-distance data transmission. To establish this network, efficient communication between the UAVs is the most vital point. Additionally, due to mobility, the topology changes frequently, leading to potential collisions and packet losses. Therefore, in this paper, a minimum distance clustering scheme (MDCS)-based FANET is proposed, where the topology is controlled by a back-off mechanism and network connectivity is maintained even when the UAVs are moving at different altitudes by calculating the relative velocity on a 3D platform while considering the randomized path-based 3D mobility model. An efficient cluster build-up process and a method for determining the position of the cluster head (CH) are introduced to control the cluster proficiently. An analytical study is performed considering Rayleigh, Nakagami-m, and Rician fading channels. Moreover, the obtained Monte Carlo simulation results justify the analytical findings. Finally, the simulations show better results than existing work in terms of throughput with changes in distance, velocity, and the number of UAVs, as well as outage probability, packet dropping rate, and delay. In the case of the Rician fading channel, for 40 UAVs, a cluster size of 7 or fewer is more favorable, showing a maximum connection distance of 165 m, a maximum throughput of 10.2 Mbps, and a maximum delay of 55.57 ms.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"56 ","pages":"Article 100971"},"PeriodicalIF":6.5,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0