LLMKey: LLM-Powered Wireless Key Generation Scheme for Next-Gen IoV Systems

TL;DR

The paper tackles secure key generation in highly dynamic IoV environments by addressing inefficiencies in channel probing and quantization. It introduces LLMKey, an LLM-powered framework that uses skipped channel probing with LLM-based channel information recovery and a PCS-based key delivery scheme that eliminates the need for traditional quantization and reconciliation. The approach is augmented by privacy amplification and real-world evaluations across V2I and V2V scenarios, demonstrating high key agreement rates (average around $0.9878$) and robustness to varying probing ratios. This work offers a practical, scalable method to establish cryptographic keys in IoV, reducing energy consumption while enhancing security for next-generation vehicular networks.

Abstract

Wireless key generation holds significant promise for establishing cryptographic keys in Next-Gen Internet of Vehicles (IoV) systems. However, existing approaches often face inefficiencies and performance limitations caused by frequent channel probing and ineffective quantization. To address these challenges, this paper introduces LLMKey, a novel key generation system designed to enhance efficiency and security. We identify excessive channel probing and suboptimal quantization as critical bottlenecks in current methods. To mitigate these issues, we propose an innovative large language model (LLM)-based channel probing technique that leverages the capabilities of LLMs to reduce probing rounds while preserving crucial channel information. Instead of conventional quantization, LLMKey adopts a perturbed compressed sensing-based key delivery mechanism, improving both robustness and security. Extensive evaluations are conducted in four real-world scenarios, encompassing V2I (Vehicle-to-Infrastructure) and V2V (Vehicle-to-Vehicle) settings in both urban and rural environments. The results show that LLMKey achieves an average key agreement rate of 98.78\%, highlighting its effectiveness and reliability across diverse conditions.

Figures (6)

• Figure 1: IoV communication scenarios.
• Figure 2: System workflow.
• Figure 3: Chain-of-thought prompt design for LLMKey.
• Figure 4: Channel recovery results.
• Figure 5: Experimental setup.