🤖 AI Summary
Security and communication risks posed by anomalous vehicles in vehicular networks demand urgent attention. This paper proposes an edge–cloud collaborative framework for detecting abnormal driving behavior: a fine-tuned, lightweight open-weight large language model—Mistral-7B—is deployed at the edge for low-latency, real-time detection; while a more capable cloud-based LLM supports deep semantic analysis and decision validation. Our key contributions include: (i) the first adaptation of Mistral-7B to vehicular cybersecurity anomaly detection; (ii) a novel hierarchical inference architecture; and (iii) a systematic characterization of the trade-off between time-window size, detection accuracy, and computational efficiency. Evaluated on an extended, manually annotated VeReMi dataset, our method achieves 98% accuracy—substantially outperforming LLaMA2-7B and RoBERTa baselines. Experimental results confirm feasibility of edge deployment and demonstrate millisecond-level response latency.
📝 Abstract
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.