Vehicular networks are exposed to various threats resulting from malicious attacks. These threats compromise the security and reliability of communications among road users, thereby jeopardizing road and traffic safety. One of the main vectors of these attacks within vehicular networks is misbehaving vehicles. To address this challenge, we propose deploying a pretrained Large Language Model (LLM)-empowered Misbehavior Detection System (MDS) within an edge-cloud detection framework. Specifically, we fine-tune Mistral-7B, a state-of-the-art LLM, as the edge component to enable real-time detection, whereas a larger LLM deployed in the cloud can conduct a more comprehensive analysis. Our experiments conducted on the extended VeReMi dataset demonstrate Mistral-7B's superior performance, achieving 98\% accuracy compared to other LLMs such as LLAMA2-7B and RoBERTa. Additionally, we investigate the impact of window size on computational costs to optimize deployment efficiency. Leveraging LLMs in MDS shows interesting results in improving the detection of vehicle misbehavior, consequently strengthening vehicular network security to ensure the safety of road users.

翻译：车载网络面临由恶意攻击引发的多种威胁。这些威胁损害道路使用者间通信的安全性与可靠性，进而危及道路与交通安全。车载网络中此类攻击的主要载体之一是行为异常的车辆。为应对这一挑战，我们提出在边缘-云检测框架内部署基于预训练大语言模型的异常行为检测系统。具体而言，我们微调前沿大语言模型Mistral-7B作为边缘组件以实现实时检测，而部署在云端的更大规模语言模型可执行更全面的分析。在扩展版VeReMi数据集上开展的实验表明，Mistral-7B相比LLAMA2-7B、RoBERTa等其他大语言模型具有更优性能，准确率达到98%。此外，我们研究了窗口尺寸对计算成本的影响以优化部署效率。在大语言模型赋能异常行为检测系统的应用中，提升车辆异常行为检测能力展现出显著效果，从而增强车载网络安全性以保障道路使用者安全。