Vehicular Communications最新文献_第2页

Securing short-packet transmissions via partial NOMA: Performance analysis under keyhole fading 通过局部NOMA保护短包传输：锁孔衰落下的性能分析

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2026-01-10 DOI: 10.1016/j.vehcom.2026.100999

Sang-Quang Nguyen , Duy Tran Trung , Lam-Thanh Tu , Anh Le-Thi , Mui Van Nguyen

This paper proposes a novel secure downlink framework that integrates Partial Non-Orthogonal Multiple Access (PNOMA) with short-packet communications (SPC) under keyhole fading channels, tailored for ultra-reliable low-latency (URLLC) services. Unlike prior studies that addressed NOMA, SPC, or keyhole effects in isolation, our work is the first to jointly consider all three aspects in a unified design. Closed-form expressions for the average secure block error rate (SBLER) and block error rate (BLER) are derived under both partial and full transmission information (PTI/FTI) assumptions at the eavesdropper, together with asymptotic analysis capturing the impact of blocklength, power allocation, and keyhole severity. Numerical simulations confirm that the proposed PNOMA-SPC system consistently outperforms conventional NOMA scheme in terms of latency, reliability, and secrecy, even under strong eavesdropping conditions. These contributions provide new theoretical and practical insights into the secure design of multiple access schemes for next-generation 6G URLLC scenarios.

本文提出了一种新的安全下行链路框架，该框架将部分非正交多址（PNOMA）与锁孔衰落信道下的短包通信（SPC）相结合，为超可靠低延迟（URLLC）业务量身定制。与先前的研究不同，我们的工作是第一个在统一设计中共同考虑所有三个方面的研究，这些研究分别解决了NOMA、SPC或锁孔效应。在窃听者的部分和完全传输信息（PTI/FTI）假设下，推导了平均安全块错误率（SBLER）和块错误率（BLER）的封闭表达式，并对块长度、功率分配和锁孔严重性的影响进行了渐近分析。数值模拟证实，即使在强窃听条件下，所提出的PNOMA-SPC系统在延迟、可靠性和保密性方面始终优于传统的NOMA方案。这些贡献为下一代6G URLLC场景下多址方案的安全设计提供了新的理论和实践见解。

{"title":"Securing short-packet transmissions via partial NOMA: Performance analysis under keyhole fading","authors":"Sang-Quang Nguyen , Duy Tran Trung , Lam-Thanh Tu , Anh Le-Thi , Mui Van Nguyen","doi":"10.1016/j.vehcom.2026.100999","DOIUrl":"10.1016/j.vehcom.2026.100999","url":null,"abstract":"<div><div>This paper proposes a novel secure downlink framework that integrates Partial Non-Orthogonal Multiple Access (PNOMA) with short-packet communications (SPC) under keyhole fading channels, tailored for ultra-reliable low-latency (URLLC) services. Unlike prior studies that addressed NOMA, SPC, or keyhole effects in isolation, our work is the first to jointly consider all three aspects in a unified design. Closed-form expressions for the average secure block error rate (SBLER) and block error rate (BLER) are derived under both partial and full transmission information (PTI/FTI) assumptions at the eavesdropper, together with asymptotic analysis capturing the impact of blocklength, power allocation, and keyhole severity. Numerical simulations confirm that the proposed PNOMA-SPC system consistently outperforms conventional NOMA scheme in terms of latency, reliability, and secrecy, even under strong eavesdropping conditions. These contributions provide new theoretical and practical insights into the secure design of multiple access schemes for next-generation 6G URLLC scenarios.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"58 ","pages":"Article 100999"},"PeriodicalIF":6.5,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145957191","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 secure GNN-MADDPG framework with combinatorial action optimization for task offloading in vehicular networks 基于组合动作优化的车辆网络任务卸载安全GNN-MADDPG框架

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2026-01-06 DOI: 10.1016/j.vehcom.2026.101000

Yabin Zhu , Xu Zhao , Xin Zhang

Vehicle-to-Everything (V2X) technology is rapidly developing. However, vehicular devices operate with limited computational power and energy. These constraints pose significant challenges for secure and energy-efficient task offloading. To address these challenges, this paper proposes a novel framework that integrates a Graph Neural Network (GNN) with the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm for secure task offloading and resource allocation. The framework employs a GNN (GraphSAGE) to capture the dynamic network topology and global interference, overcoming the limitations of partial observability. This spatial feature representation supports coordinated decision-making by multiple agents within the MADDPG architecture. To handle the high-dimensional and coupled action space, a combinatorial action selection strategy is proposed and QMIX value function decomposition is adopted. This “optimize-then-combine” mechanism enables efficient joint optimization of continuous resources and discrete decisions. Furthermore, a hybrid RSA-AES encryption scheme combined with frequency hopping is implemented to ensure end-to-end data security and anti-jamming capabilities. Extensive comparative experiments demonstrated that the proposed framework significantly outperformed baseline methods, including DQN and standard MADDPG, in terms of task completion rate, average latency, and energy consumption, especially in high-load scenarios. Ablation studies further validated the critical contributions of the GNN, combinatorial action design, and security mechanisms. This work provides an efficient, secure, and scalable solution for resource optimization in complex V2X environments.

车联网（V2X）技术正在迅速发展。然而，车载设备在有限的计算能力和能量下运行。这些限制为安全和节能的任务卸载带来了重大挑战。为了解决这些挑战，本文提出了一个新的框架，该框架将图神经网络（GNN）与多智能体深度确定性策略梯度（MADDPG）算法集成在一起，用于安全任务卸载和资源分配。该框架采用GNN （GraphSAGE）捕获动态网络拓扑和全局干扰，克服了部分可观测性的限制。这种空间特征表示支持MADDPG体系结构中多个代理的协调决策。针对高维、耦合的动作空间，提出了组合动作选择策略，并采用QMIX值函数分解。这种“先优化后组合”的机制可以实现连续资源和离散决策的有效联合优化。此外，还实现了一种结合跳频的混合RSA-AES加密方案，以确保端到端数据安全和抗干扰能力。大量的对比实验表明，所提出的框架在任务完成率、平均延迟和能耗方面明显优于基准方法，包括DQN和标准MADDPG，特别是在高负载场景下。消融研究进一步验证了GNN、组合作用设计和安全机制的重要贡献。这项工作为复杂V2X环境中的资源优化提供了高效、安全、可扩展的解决方案。

{"title":"A secure GNN-MADDPG framework with combinatorial action optimization for task offloading in vehicular networks","authors":"Yabin Zhu , Xu Zhao , Xin Zhang","doi":"10.1016/j.vehcom.2026.101000","DOIUrl":"10.1016/j.vehcom.2026.101000","url":null,"abstract":"<div><div>Vehicle-to-Everything (V2X) technology is rapidly developing. However, vehicular devices operate with limited computational power and energy. These constraints pose significant challenges for secure and energy-efficient task offloading. To address these challenges, this paper proposes a novel framework that integrates a Graph Neural Network (GNN) with the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm for secure task offloading and resource allocation. The framework employs a GNN (GraphSAGE) to capture the dynamic network topology and global interference, overcoming the limitations of partial observability. This spatial feature representation supports coordinated decision-making by multiple agents within the MADDPG architecture. To handle the high-dimensional and coupled action space, a combinatorial action selection strategy is proposed and QMIX value function decomposition is adopted. This “optimize-then-combine” mechanism enables efficient joint optimization of continuous resources and discrete decisions. Furthermore, a hybrid RSA-AES encryption scheme combined with frequency hopping is implemented to ensure end-to-end data security and anti-jamming capabilities. Extensive comparative experiments demonstrated that the proposed framework significantly outperformed baseline methods, including DQN and standard MADDPG, in terms of task completion rate, average latency, and energy consumption, especially in high-load scenarios. Ablation studies further validated the critical contributions of the GNN, combinatorial action design, and security mechanisms. This work provides an efficient, secure, and scalable solution for resource optimization in complex V2X environments.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"58 ","pages":"Article 101000"},"PeriodicalIF":6.5,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145902773","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

Challenges and opportunities of synthetic data generation for machine learning-based intrusion detection systems in in-vehicle networks 基于机器学习的车载网络入侵检测系统合成数据生成的挑战与机遇

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2026-01-01 DOI: 10.1016/j.vehcom.2025.100998

Junhui Li , Nikolaos Ersotelos , Michail-Antisthenis Tsompanas , Gregory Epiphaniou

Machine learning-based intrusion detection systems (ML-IDS) for in-vehicle networks require diverse, high-quality datasets that are scarce because of privacy and data collection challenges. Collecting data in the real world often faces challenges, such as a lack of detailed attack scenarios and significant resource requirements. This survey examines synthetic data generation (SDG) as a solution and systematically reviews SDG methods, ML-IDS models, and their intersection in automotive security, which has not been addressed in prior surveys. We introduce a quantitative evaluation framework and apply it to synthetic and real datasets, such as SynCAN (Synthetic Controller Area Network), CAN-MIRGU (CAN Multi-Information Record Generating Unit) and Real ORNL (Oak Ridge National Laboratory) Automotive Dynamometer (ROAD) dataset. The results reveal critical limitations, since current synthetic approaches show reduced identifier coverage and unrealistic temporal patterns. Additionally, spatial network topology analysis reveals that synthetic datasets lack the hierarchical hub-and-spoke communication structures and functional subsystem coupling characteristic of real vehicular networks. Through a comprehensive analysis of more than 50 papers published in the time period from 2018 to 2025, we identified five research gaps,including temporal fidelity preservation, real-time constraints, cross-vehicle generalisation, attack diversity limitations, and quality validation requirements. Although SDG promises to address data scarcity and enable complex attack scenario simulations, current methods inadequately model authentic vehicular communications. We provide guidelines for developing temporally aware generation models and validation frameworks for practical deployment.

用于车载网络的基于机器学习的入侵检测系统（ML-IDS）需要多样化、高质量的数据集，而这些数据集由于隐私和数据收集方面的挑战而稀缺。在现实世界中收集数据经常面临挑战，例如缺乏详细的攻击场景和大量的资源需求。本调查将合成数据生成（SDG）作为一种解决方案进行了研究，并系统地回顾了SDG方法、ML-IDS模型及其在汽车安全中的交叉，这在以前的调查中没有得到解决。我们引入了一个定量评估框架，并将其应用于合成数据集和实际数据集，如SynCAN（合成控制器局域网）、CAN- mirgu （CAN多信息记录生成单元）和real ORNL（橡树岭国家实验室）汽车测量仪（ROAD）数据集。结果揭示了关键的局限性，因为当前的综合方法显示出标识符覆盖率降低和不切实际的时间模式。此外，空间网络拓扑分析表明，合成数据集缺乏真实车辆网络的层次化轮辐通信结构和功能子系统耦合特征。通过对2018年至2025年期间发表的50多篇论文的综合分析，我们确定了五个研究空白，包括时间保真度保存、实时约束、跨车辆概括、攻击多样性限制和质量验证要求。尽管可持续发展目标承诺解决数据短缺问题，并实现复杂的攻击场景模拟，但目前的方法无法充分模拟真实的车辆通信。我们为实际部署提供了开发临时感知生成模型和验证框架的指导方针。

{"title":"Challenges and opportunities of synthetic data generation for machine learning-based intrusion detection systems in in-vehicle networks","authors":"Junhui Li , Nikolaos Ersotelos , Michail-Antisthenis Tsompanas , Gregory Epiphaniou","doi":"10.1016/j.vehcom.2025.100998","DOIUrl":"10.1016/j.vehcom.2025.100998","url":null,"abstract":"<div><div>Machine learning-based intrusion detection systems (ML-IDS) for in-vehicle networks require diverse, high-quality datasets that are scarce because of privacy and data collection challenges. Collecting data in the real world often faces challenges, such as a lack of detailed attack scenarios and significant resource requirements. This survey examines synthetic data generation (SDG) as a solution and systematically reviews SDG methods, ML-IDS models, and their intersection in automotive security, which has not been addressed in prior surveys. We introduce a quantitative evaluation framework and apply it to synthetic and real datasets, such as SynCAN (Synthetic Controller Area Network), CAN-MIRGU (CAN Multi-Information Record Generating Unit) and Real ORNL (Oak Ridge National Laboratory) Automotive Dynamometer (ROAD) dataset. The results reveal critical limitations, since current synthetic approaches show reduced identifier coverage and unrealistic temporal patterns. Additionally, spatial network topology analysis reveals that synthetic datasets lack the hierarchical hub-and-spoke communication structures and functional subsystem coupling characteristic of real vehicular networks. Through a comprehensive analysis of more than 50 papers published in the time period from 2018 to 2025, we identified five research gaps,including temporal fidelity preservation, real-time constraints, cross-vehicle generalisation, attack diversity limitations, and quality validation requirements. Although SDG promises to address data scarcity and enable complex attack scenario simulations, current methods inadequately model authentic vehicular communications. We provide guidelines for developing temporally aware generation models and validation frameworks for practical deployment.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"58 ","pages":"Article 100998"},"PeriodicalIF":6.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145894649","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

Enhancing quantum-resistant data privacy in vehicular cloud networks using NIST-qualified FALCON algorithm 利用nist合格的FALCON算法增强车载云网络中抗量子数据隐私

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-12-30 DOI: 10.1016/j.vehcom.2025.100995

Mritunjay Shall Peelam , Brijesh Kumar Chaurasia , Man Mohan Shukla , Vinay Chamola

Road safety, congestion, pollution, and data security are critical challenges in the development of smart transportation systems. Vehicular Ad-hoc Networks (VANETs) form the backbone of such systems by enabling real-time communication, accident management, and traffic monitoring. However, the vast data generated in VANETs is increasingly vulnerable in the post-quantum era, where traditional cryptographic methods like RSA, ECC, and DSA fail to withstand quantum attacks. To address this, we propose the integration of the NIST-qualified Falcon algorithm, a lattice-based post-quantum cryptographic scheme, to ensure confidentiality, integrity, and resilience of vehicular communication. The proposed scheme is implemented and evaluated in a Vehicular Network Cloud (VNC) environment on different computational platforms, including Apple Silicon M1 Max and AMD Ryzen systems. Experimental results demonstrate that Falcon achieves practical signing and verification delays (22 ms and 17 ms on M1), while maintaining robust key generation performance even at higher bit lengths. Comparative analysis with RSA and ECC shows Falcon’s superiority in quantum resistance and a balanced trade-off between computational cost and communication efficiency. Although Falcon incurs relatively higher encryption and decryption delays, its security guarantees and scalability make it a strong candidate for deployment in VANETs. This research confirms that Falcon provides a feasible, quantum-resistant solution for securing smart transportation ecosystems while meeting the stringent real-time requirements of vehicular communications.

道路安全、拥堵、污染和数据安全是智能交通系统发展的关键挑战。车辆自组织网络（VANETs）通过实现实时通信、事故管理和交通监控，构成了此类系统的骨干。然而，VANETs中产生的大量数据在后量子时代变得越来越脆弱，传统的加密方法如RSA、ECC、DSA等无法抵御量子攻击。为了解决这个问题，我们提出了集成nist合格的Falcon算法，这是一种基于晶格的后量子加密方案，以确保车辆通信的保密性、完整性和弹性。该方案在不同计算平台（包括Apple Silicon M1 Max和AMD Ryzen系统）上的车辆网络云（VNC）环境中进行了实施和评估。实验结果表明，Falcon实现了实际的签名和验证延迟（在M1上分别为22 ms和17 ms），同时即使在较高的位长度下也能保持稳健的密钥生成性能。与RSA和ECC的比较分析表明，Falcon在量子抗性方面具有优势，并且在计算成本和通信效率之间进行了平衡权衡。尽管Falcon会导致相对较高的加密和解密延迟，但其安全性保证和可扩展性使其成为部署在vanet中的有力候选者。这项研究证实，Falcon为保护智能交通生态系统提供了一种可行的、抗量子的解决方案，同时满足了车辆通信的严格实时要求。

{"title":"Enhancing quantum-resistant data privacy in vehicular cloud networks using NIST-qualified FALCON algorithm","authors":"Mritunjay Shall Peelam , Brijesh Kumar Chaurasia , Man Mohan Shukla , Vinay Chamola","doi":"10.1016/j.vehcom.2025.100995","DOIUrl":"10.1016/j.vehcom.2025.100995","url":null,"abstract":"<div><div>Road safety, congestion, pollution, and data security are critical challenges in the development of smart transportation systems. Vehicular Ad-hoc Networks (VANETs) form the backbone of such systems by enabling real-time communication, accident management, and traffic monitoring. However, the vast data generated in VANETs is increasingly vulnerable in the post-quantum era, where traditional cryptographic methods like RSA, ECC, and DSA fail to withstand quantum attacks. To address this, we propose the integration of the NIST-qualified Falcon algorithm, a lattice-based post-quantum cryptographic scheme, to ensure confidentiality, integrity, and resilience of vehicular communication. The proposed scheme is implemented and evaluated in a Vehicular Network Cloud (VNC) environment on different computational platforms, including Apple Silicon M1 Max and AMD Ryzen systems. Experimental results demonstrate that Falcon achieves practical signing and verification delays (22 ms and 17 ms on M1), while maintaining robust key generation performance even at higher bit lengths. Comparative analysis with RSA and ECC shows Falcon’s superiority in quantum resistance and a balanced trade-off between computational cost and communication efficiency. Although Falcon incurs relatively higher encryption and decryption delays, its security guarantees and scalability make it a strong candidate for deployment in VANETs. This research confirms that Falcon provides a feasible, quantum-resistant solution for securing smart transportation ecosystems while meeting the stringent real-time requirements of vehicular communications.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"58 ","pages":"Article 100995"},"PeriodicalIF":6.5,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145894647","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

Secure and efficient V2ES authentication protocol and faster-RCNN based object detection scheme for connected autonomous vehicles 安全高效的V2ES认证协议和基于更快rcnn的网联自动驾驶汽车目标检测方案

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-12-24 DOI: 10.1016/j.vehcom.2025.100997

Shucheng Ying , Xiumei Li , Qi Xie

Connected Autonomous Vehicles (CAVs) can significantly enhance perception accuracy, optimize driving routes, and improve traffic efficiency and safety through collaborative road environment sensing. However, sharing image data among vehicles raises serious privacy concerns. Although various privacy-preserving computation techniques, such as homomorphic encryption, garbled circuits, and additive secret sharing, have been proposed to address this issue, most existing methods lack secure communication protocols between vehicles and edge servers (Vehicle-to-Edge Server, V2ES) as well as between edge servers. As a result, they remain vulnerable to collusion attacks, device capture attacks, and side-channel attacks, as well as incur high computational overhead. To address these challenges, an efficient and privacy-preserving computation scheme designed specifically for the faster region-convolutional neural network (R-CNN) object detection of CAVs is proposed, which has several advantages: (1) The first safe and practical object detection system model for CAVs is established; (2) The first secure and lightweight road side unit(RSU)-assisted V2ES authentication protocol and secure communication mechanism between edge servers are proposed to effectively resist collusion attacks and side channel attacks in the object detection scheme for CAVs; and (3) The multiplication and division protocols of Bi et al.’s scheme are optimized, significantly improving both computational and communication efficiency. The proposed RSU-assisted V2ES authentication protocol is provably secure under the Canetti-Krawczyk (CK) model and the extended security model. The experimental results further confirm that the proposed scheme significantly improves computational performance while ensuring data privacy, with multiplication efficiency improved by about 3.13 times and its communication overhead reduced by 50%, and division efficiency improved by 2.26 times and its communication overhead reduced by 60%.

互联自动驾驶汽车（cav）可以通过协同道路环境感知，显著提高感知精度，优化行驶路线，提高交通效率和安全性。然而，在车辆之间共享图像数据引发了严重的隐私问题。尽管已经提出了各种保护隐私的计算技术，如同态加密、乱码电路和加性秘密共享，以解决这个问题，但大多数现有方法缺乏车辆和边缘服务器之间（车对边缘服务器，V2ES）以及边缘服务器之间的安全通信协议。因此，它们仍然容易受到合谋攻击、设备捕获攻击和侧信道攻击，并且会产生很高的计算开销。针对这些挑战，本文提出了一种针对快速区域卷积神经网络（R-CNN）自动驾驶汽车目标检测的高效且保护隐私的计算方案，该方案具有以下优点：(1)建立了第一个安全实用的自动驾驶汽车目标检测系统模型；(2)首次提出安全轻量级的RSU辅助V2ES认证协议和边缘服务器间安全通信机制，有效抵御自动驾驶汽车目标检测方案中的串通攻击和侧信道攻击；(3)对Bi等人方案的乘法和除法协议进行了优化，显著提高了计算效率和通信效率。在Canetti-Krawczyk （CK）模型和扩展安全模型下证明了rsu辅助V2ES认证协议的安全性。实验结果进一步证实，该方案在保证数据保密性的同时，显著提高了计算性能，乘法效率提高约3.13倍，通信开销降低50%；除法效率提高约2.26倍，通信开销降低60%。

{"title":"Secure and efficient V2ES authentication protocol and faster-RCNN based object detection scheme for connected autonomous vehicles","authors":"Shucheng Ying , Xiumei Li , Qi Xie","doi":"10.1016/j.vehcom.2025.100997","DOIUrl":"10.1016/j.vehcom.2025.100997","url":null,"abstract":"<div><div>Connected Autonomous Vehicles (CAVs) can significantly enhance perception accuracy, optimize driving routes, and improve traffic efficiency and safety through collaborative road environment sensing. However, sharing image data among vehicles raises serious privacy concerns. Although various privacy-preserving computation techniques, such as homomorphic encryption, garbled circuits, and additive secret sharing, have been proposed to address this issue, most existing methods lack secure communication protocols between vehicles and edge servers (Vehicle-to-Edge Server, V2ES) as well as between edge servers. As a result, they remain vulnerable to collusion attacks, device capture attacks, and side-channel attacks, as well as incur high computational overhead. To address these challenges, an efficient and privacy-preserving computation scheme designed specifically for the faster region-convolutional neural network (R-CNN) object detection of CAVs is proposed, which has several advantages: (1) The first safe and practical object detection system model for CAVs is established; (2) The first secure and lightweight road side unit(RSU)-assisted V2ES authentication protocol and secure communication mechanism between edge servers are proposed to effectively resist collusion attacks and side channel attacks in the object detection scheme for CAVs; and (3) The multiplication and division protocols of Bi et al.’s scheme are optimized, significantly improving both computational and communication efficiency. The proposed RSU-assisted V2ES authentication protocol is provably secure under the Canetti-Krawczyk (CK) model and the extended security model. The experimental results further confirm that the proposed scheme significantly improves computational performance while ensuring data privacy, with multiplication efficiency improved by about 3.13 times and its communication overhead reduced by 50%, and division efficiency improved by 2.26 times and its communication overhead reduced by 60%.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"58 ","pages":"Article 100997"},"PeriodicalIF":6.5,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145823369","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

The role of large language models (LLMs) in enhancing intelligent transportation systems: A survey 大语言模型（LLMs）在增强智能交通系统中的作用：一项调查

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-12-22 DOI: 10.1016/j.vehcom.2025.100996

Vikas Hassija , Tamonash Majumder , Debangshu Roy , Raja Piyush , Vinay Chamola

Large Language Models (LLMs) are transforming Intelligent Transportation Systems (ITS) by shifting operations from static, rule based systems toward adaptive, data-driven decision-making. This paper presents a comprehensive methodological and application-focused survey of LLMs in ITS, grounded in transformer-based architectures like GPT-4, BERT, and LlaMa. We analyze the technical challenge of integrating diverse multimodal data including sensor logs, visual inputs, and textual reports via cross-modal fusion strategies. The survey examines key applications such as traffic signal optimization, predictive maintenance, V2X communication, public transport scheduling, and route personalization. Furthermore, we detail core methodologies (e.g., fine- tuning, Chain-of-Thought prompting, federated learning, RLHF) used to enhance LLM performance under real-time conditions and assess explainability frameworks (SHAP, LIME) to foster trust. We also identify critical challenges, including model hallucination, privacy risks, resource demands, and latency constraints. By synthesizing insights from over 200 primary research contributions, this work offers a foundational reference for designing scalable, intelligent, and ethically aligned ITS architectures.

大型语言模型（llm）正在改变智能交通系统（ITS），将操作从静态的、基于规则的系统转变为自适应的、数据驱动的决策。本文以GPT-4、BERT和LlaMa等基于变压器的架构为基础，介绍了ITS中llm的综合方法和应用调查。我们分析了通过跨模态融合策略整合多种多模态数据的技术挑战，包括传感器日志、视觉输入和文本报告。该调查考察了交通信号优化、预测性维护、V2X通信、公共交通调度和路线个性化等关键应用。此外，我们详细介绍了核心方法（例如，微调，思维链提示，联邦学习，RLHF）用于提高LLM在实时条件下的性能，并评估可解释性框架（SHAP， LIME）以促进信任。我们还确定了关键的挑战，包括模型幻觉、隐私风险、资源需求和延迟限制。通过综合来自200多个主要研究贡献的见解，这项工作为设计可扩展，智能和道德一致的ITS架构提供了基础参考。

{"title":"The role of large language models (LLMs) in enhancing intelligent transportation systems: A survey","authors":"Vikas Hassija , Tamonash Majumder , Debangshu Roy , Raja Piyush , Vinay Chamola","doi":"10.1016/j.vehcom.2025.100996","DOIUrl":"10.1016/j.vehcom.2025.100996","url":null,"abstract":"<div><div>Large Language Models (LLMs) are transforming Intelligent Transportation Systems (ITS) by shifting operations from static, rule based systems toward adaptive, data-driven decision-making. This paper presents a comprehensive methodological and application-focused survey of LLMs in ITS, grounded in transformer-based architectures like GPT-4, BERT, and LlaMa. We analyze the technical challenge of integrating diverse multimodal data including sensor logs, visual inputs, and textual reports via cross-modal fusion strategies. The survey examines key applications such as traffic signal optimization, predictive maintenance, V2X communication, public transport scheduling, and route personalization. Furthermore, we detail core methodologies (e.g., fine- tuning, Chain-of-Thought prompting, federated learning, RLHF) used to enhance LLM performance under real-time conditions and assess explainability frameworks (SHAP, LIME) to foster trust. We also identify critical challenges, including model hallucination, privacy risks, resource demands, and latency constraints. By synthesizing insights from over 200 primary research contributions, this work offers a foundational reference for designing scalable, intelligent, and ethically aligned ITS architectures.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"58 ","pages":"Article 100996"},"PeriodicalIF":6.5,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145813956","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

Lightweight anonymous aggregate authentication in VANET based on offline/online certificateless signcryption using one-time key 基于一次性密钥离线/在线无证书签名的VANET轻量级匿名聚合认证

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-12-20 DOI: 10.1016/j.vehcom.2025.100994

Abdullahi Yahya Imam , Fagen Li , Hamisu Ibrahim Usman , Muhammad Hanif Tunio

Recent developments in the internet of things (IoT) and vehicular ad hoc network (VANET) significantly improve traffic management and safety. At the same time, several security challenges come alongside these improvements. Numerous research works have proposed different solutions to these security challenges using various cryptographic techniques. To maximize efficiency, recent works have developed several certificateless aggregate signcryption (CLASC) schemes without using the expensive bilinear pairing operations. However, recent studies have revealed various security flaws in many schemes, making them vulnerable to key replacement attacks that can lead to impersonation. Considering these security issues and the significance of high performance, we develop a novel pairing-free CLASC scheme for anonymous authentication in VANETs. To further improve the performance especially for real time communication, we devised a method of shifting the time consuming computations to offline operations. The confidentiality and unforgeability security of this scheme have been proved formally in random oracle model (ROM). Further analysis has demonstrated that the proposed scheme achieves other security requirements essential for anonymous authentication in VANET. Analysis of performances has shown that our scheme has shortest average transmission delay, specifically due to its very low computational overhead.

物联网（IoT）和车载自组织网络（VANET）的最新发展显著改善了交通管理和安全。与此同时，随着这些改进，也出现了一些安全挑战。针对这些安全挑战，许多研究工作已经提出了使用各种加密技术的不同解决方案。为了最大限度地提高效率，最近的研究开发了几种不使用昂贵的双线性配对操作的无证书聚合签名加密（class）方案。然而，最近的研究揭示了许多方案中的各种安全漏洞，使它们容易受到可能导致冒充的密钥替换攻击。考虑到这些安全问题和高性能的重要性，我们开发了一种新的无配对的class匿名认证方案。为了进一步提高性能，特别是在实时通信方面，我们设计了一种将耗时的计算转移到离线操作的方法。该方案的保密性和不可伪造性在随机oracle模型（ROM）中得到了正式证明。进一步的分析表明，该方案满足了VANET中匿名认证的其他安全要求。性能分析表明，我们的方案具有最短的平均传输延迟，特别是由于它的计算开销非常低。

{"title":"Lightweight anonymous aggregate authentication in VANET based on offline/online certificateless signcryption using one-time key","authors":"Abdullahi Yahya Imam , Fagen Li , Hamisu Ibrahim Usman , Muhammad Hanif Tunio","doi":"10.1016/j.vehcom.2025.100994","DOIUrl":"10.1016/j.vehcom.2025.100994","url":null,"abstract":"<div><div>Recent developments in the internet of things (IoT) and vehicular ad hoc network (VANET) significantly improve traffic management and safety. At the same time, several security challenges come alongside these improvements. Numerous research works have proposed different solutions to these security challenges using various cryptographic techniques. To maximize efficiency, recent works have developed several certificateless aggregate signcryption (CLASC) schemes without using the expensive bilinear pairing operations. However, recent studies have revealed various security flaws in many schemes, making them vulnerable to key replacement attacks that can lead to impersonation. Considering these security issues and the significance of high performance, we develop a novel pairing-free CLASC scheme for anonymous authentication in VANETs. To further improve the performance especially for real time communication, we devised a method of shifting the time consuming computations to offline operations. The confidentiality and unforgeability security of this scheme have been proved formally in random oracle model (ROM). Further analysis has demonstrated that the proposed scheme achieves other security requirements essential for anonymous authentication in VANET. Analysis of performances has shown that our scheme has shortest average transmission delay, specifically due to its very low computational overhead.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"58 ","pages":"Article 100994"},"PeriodicalIF":6.5,"publicationDate":"2025-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145796044","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

Cooperative control of heterogeneous vehicle platoons under communication time–varying delays and intermittent observations 通信时变延迟和间歇观测条件下异构车辆排的协同控制

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-12-07 DOI: 10.1016/j.vehcom.2025.100993

Yilin Wu , Qian Zhao , Yonggui Liu , Zeming Li , Zhiping Shen

This article discusses the cooperative control problem for heterogeneous vehicle platoons subject to non-ideal factors, specifically communication time-varying delays, system noises and intermittent observations. The main idea is to construct the internal reference models to generate common signals for all vehicles. First, in ideal situations under a directed acyclic topology (DAT), a distributed controller is proposed based on the properties of lower triangular matrices and solving an algebraic Riccati equation (ARE); Second, for non–ideal situations under uniformly quasi-strongly connected topology, optimal states are estimated using intermittent observations, and a distributed controller is designed to maintain the platoon’s mean square stability (MSS). Compared to the control methods in existing literatures, the proposed control approaches in this paper, relying on the system’s output information rather than state information, can effectively suppress the impacts of vehicle heterogeneity and the aforementioned non–ideal factors on platoon stability. Simulations are conducted to demonstrate a superior convergence speed compared to those in the literatures.

本文讨论了受非理想因素影响的异构车辆队列协同控制问题，特别是通信时变延迟、系统噪声和间歇观测。主要思想是构建内部参考模型来生成所有车辆的公共信号。首先，在有向无环拓扑（DAT）的理想情况下，提出了一种基于下三角矩阵性质和求解代数Riccati方程（ARE）的分布式控制器；其次，对于均匀准强连接拓扑下的非理想情况，利用间歇观测估计最优状态，并设计分布式控制器来保持排的均方稳定性（MSS）。与现有文献的控制方法相比，本文提出的控制方法依靠系统的输出信息而不是状态信息，可以有效地抑制车辆异质性和上述非理想因素对车队稳定性的影响。仿真结果表明，该方法具有较好的收敛速度。

{"title":"Cooperative control of heterogeneous vehicle platoons under communication time–varying delays and intermittent observations","authors":"Yilin Wu , Qian Zhao , Yonggui Liu , Zeming Li , Zhiping Shen","doi":"10.1016/j.vehcom.2025.100993","DOIUrl":"10.1016/j.vehcom.2025.100993","url":null,"abstract":"<div><div>This article discusses the cooperative control problem for heterogeneous vehicle platoons subject to non-ideal factors, specifically communication time-varying delays, system noises and intermittent observations. The main idea is to construct the internal reference models to generate common signals for all vehicles. First, in ideal situations under a directed acyclic topology (DAT), a distributed controller is proposed based on the properties of lower triangular matrices and solving an algebraic Riccati equation (ARE); Second, for non–ideal situations under uniformly quasi-strongly connected topology, optimal states are estimated using intermittent observations, and a distributed controller is designed to maintain the platoon’s mean square stability (MSS). Compared to the control methods in existing literatures, the proposed control approaches in this paper, relying on the system’s output information rather than state information, can effectively suppress the impacts of vehicle heterogeneity and the aforementioned non–ideal factors on platoon stability. Simulations are conducted to demonstrate a superior convergence speed compared to those in the literatures.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"57 ","pages":"Article 100993"},"PeriodicalIF":6.5,"publicationDate":"2025-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689755","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

V-PISL:Post-quantum identity-based signature scheme over lattice for VANETs 基于点阵的VANETs后量子身份签名方案

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-11-28 DOI: 10.1016/j.vehcom.2025.100992

Xiang Zou , Deng Pan , Guozhen Shi , Shuhan Yu , Jianguo Xie

As intelligent transportation advances, the backbone of smart mobility is Vehicular Ad Hoc Networks (VANETs), which nevertheless remain vulnerable to security threats stemming from high node mobility, dynamic topologies, and open wireless channels. Traditional security frameworks grapple with cumbersome key management in VANETs’ dynamic ecosystems, while quantum computing poses a fundamental threat to conventional cryptographic protocols. Existing post-quantum signature schemes often suffer from oversized keys and signatures, coupled with reliance on complex operations like trapdoor generation, limiting their applicability to resource-constrained vehicular devices.We propose V-PISL, a lattice-based post-quantum identity-based signature scheme tailored for VANETs. Built on the Dilithium framework and algebraic lattices, it eliminates trapdoor mechanisms, with security grounded in the Module Short Integer Solution (MSIS) and Module Learning With Errors (MLWE) problems. Experimental results demonstrate V-PISL’s efficiency across 112-bit, 169-bit, and 241-bit security levels. Its 1312-byte system public key delivers more than 91.1 % storage efficiency gains compared to the latest schemes (LB-IBS and PQ-ISS), with an overall storage efficiency improvement of 62.6 %, and the response speed reaches the millisecond level. Thus, V-PISL provides a practical postquantum security solution for resource-constrained vehicular environments.

随着智能交通的发展，智能移动的支柱是车辆自组织网络（vanet），然而，它仍然容易受到来自高节点移动性、动态拓扑和开放无线信道的安全威胁。传统的安全框架在VANETs的动态生态系统中努力解决繁琐的密钥管理问题，而量子计算对传统的加密协议构成了根本性的威胁。现有的后量子签名方案往往存在密钥和签名过大的问题，再加上对陷阱门生成等复杂操作的依赖，限制了它们在资源受限的车载设备上的适用性。我们提出了一种为VANETs量身定制的基于晶格的后量子身份签名方案V-PISL。它建立在Dilithium框架和代数格上，消除了活板门机制，其安全性基于模块短整数解决方案（MSIS）和模块错误学习（MLWE）问题。实验结果证明了V-PISL在112位、169位和241位安全级别上的有效性。其1312字节的系统公钥与最新方案（LB-IBS和PQ-ISS）相比，存储效率提高了91.1%以上，整体存储效率提高了62.6%，响应速度达到毫秒级。因此，V-PISL为资源受限的车辆环境提供了一种实用的后量子安全解决方案。

{"title":"V-PISL:Post-quantum identity-based signature scheme over lattice for VANETs","authors":"Xiang Zou , Deng Pan , Guozhen Shi , Shuhan Yu , Jianguo Xie","doi":"10.1016/j.vehcom.2025.100992","DOIUrl":"10.1016/j.vehcom.2025.100992","url":null,"abstract":"<div><div>As intelligent transportation advances, the backbone of smart mobility is Vehicular Ad Hoc Networks (VANETs), which nevertheless remain vulnerable to security threats stemming from high node mobility, dynamic topologies, and open wireless channels. Traditional security frameworks grapple with cumbersome key management in VANETs’ dynamic ecosystems, while quantum computing poses a fundamental threat to conventional cryptographic protocols. Existing post-quantum signature schemes often suffer from oversized keys and signatures, coupled with reliance on complex operations like trapdoor generation, limiting their applicability to resource-constrained vehicular devices.We propose V-PISL, a lattice-based post-quantum identity-based signature scheme tailored for VANETs. Built on the Dilithium framework and algebraic lattices, it eliminates trapdoor mechanisms, with security grounded in the Module Short Integer Solution (MSIS) and Module Learning With Errors (MLWE) problems. Experimental results demonstrate V-PISL’s efficiency across 112-bit, 169-bit, and 241-bit security levels. Its 1312-byte system public key delivers more than 91.1 % storage efficiency gains compared to the latest schemes (LB-IBS and PQ-ISS), with an overall storage efficiency improvement of 62.6 %, and the response speed reaches the millisecond level. Thus, V-PISL provides a practical postquantum security solution for resource-constrained vehicular environments.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"57 ","pages":"Article 100992"},"PeriodicalIF":6.5,"publicationDate":"2025-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145613791","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

Negotiating strict latency limits for dynamic real-time services in vehicular time-sensitive networks 车载时间敏感网络中动态实时服务的严格延迟限制协商

IF 6.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Vehicular Communications

Pub Date : 2025-11-17 DOI: 10.1016/j.vehcom.2025.100985

Timo Salomon , Lisa Maile , Philipp Meyer , Franz Korf , Thomas C. Schmidt

Future vehicles are expected to dynamically deploy in-vehicle applications within a Service-Oriented Architecture (SOA) while critical services continue to operate under hard real-time constraints. Time-Sensitive Networking (TSN) on the in-vehicle Ethernet layer is dedicated to ensure deterministic communication between critical services; its Credit-Based Shaper (CBS) supports dynamic resource reservations. However, the dynamic nature of service deployment challenges network resource configuration, since any new reservation may change the latency of already validated flows. Standard methods of worst-case latency analysis for CBS have been found incorrect, and current TSN stream reservation procedures lack mechanisms to signal application layer Quality-of-Service (QoS) requirements or verify deadlines.

In this paper, we propose and validate a QoS negotiation scheme that interacts with the TSN network controller to reserve resources while ensuring latency bounds. For the first time, this work comparatively evaluates reservation schemes using worst-case analysis and simulations of a realistic In-Vehicle Network (IVN) and demonstrates their impact on QoS guarantees, resource utilization, and setup times. We find that only one reservation scheme utilizing per-queue delay budgets and network calculus provides valid configurations and guarantees acceptable latency bounds throughout the IVN. The proposed service negotiation mechanism efficiently establishes 450 vehicular network reservations in just 11 ms.

未来的车辆预计将在面向服务的体系结构（SOA）中动态部署车载应用程序，而关键服务将继续在硬实时约束下运行。车载以太网层的时间敏感网络（TSN）致力于确保关键服务之间的确定性通信；它的基于信用的Shaper （CBS）支持动态资源保留。然而，服务部署的动态特性对网络资源配置提出了挑战，因为任何新的预约都可能改变已经验证的流的延迟。CBS的最坏情况延迟分析的标准方法被发现是不正确的，并且当前的TSN流保留过程缺乏表明应用层服务质量（QoS）要求或验证截止日期的机制。

{"title":"Negotiating strict latency limits for dynamic real-time services in vehicular time-sensitive networks","authors":"Timo Salomon , Lisa Maile , Philipp Meyer , Franz Korf , Thomas C. Schmidt","doi":"10.1016/j.vehcom.2025.100985","DOIUrl":"10.1016/j.vehcom.2025.100985","url":null,"abstract":"<div><div>Future vehicles are expected to dynamically deploy in-vehicle applications within a Service-Oriented Architecture (SOA) while critical services continue to operate under hard real-time constraints. Time-Sensitive Networking (TSN) on the in-vehicle Ethernet layer is dedicated to ensure deterministic communication between critical services; its Credit-Based Shaper (CBS) supports dynamic resource reservations. However, the dynamic nature of service deployment challenges network resource configuration, since any new reservation may change the latency of already validated flows. Standard methods of worst-case latency analysis for CBS have been found incorrect, and current TSN stream reservation procedures lack mechanisms to signal application layer Quality-of-Service (QoS) requirements or verify deadlines.</div><div>In this paper, we propose and validate a QoS negotiation scheme that interacts with the TSN network controller to reserve resources while ensuring latency bounds. For the first time, this work comparatively evaluates reservation schemes using worst-case analysis and simulations of a realistic In-Vehicle Network (IVN) and demonstrates their impact on QoS guarantees, resource utilization, and setup times. We find that only one reservation scheme utilizing per-queue delay budgets and network calculus provides valid configurations and guarantees acceptable latency bounds throughout the IVN. The proposed service negotiation mechanism efficiently establishes 450 vehicular network reservations in just 11 ms.</div></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"57 ","pages":"Article 100985"},"PeriodicalIF":6.5,"publicationDate":"2025-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145535999","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