MistralBSM: Leveraging Mistral-7B for Vehicular Networks Misbehavior Detection

📅 2024-07-26
🏛️ arXiv.org
📈 Citations: 7
Influential: 0
📄 PDF
🤖 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.

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

Detects misbehaving vehicles in vehicular networks
Uses fine-tuned Mistral-7B for real-time edge detection
Validates detection through cloud-based comprehensive analysis
Innovation

Methods, ideas, or system contributions that make the work stand out.

Fine-tunes Mistral-7B for real-time misbehavior detection
Uses edge-cloud framework with lightweight and large LLMs
Achieves high accuracy with minimal parameter updates
🔎 Similar Papers
No similar papers found.
W
Wissal Hamhoum
Department of Computer and Software Engineering, Polytechnique Montréal, Canada
S
S. Cherkaoui
Department of Computer and Software Engineering, Polytechnique Montréal, Canada