Context-Aware Authentication Framework for Secure V2V and V2I Communications in Autonomous Vehicles Using LLM

The rapid adoption of autonomous vehicles necessitates secure and efficient communication frameworks to protect against cyber threats and to ensure the privacy of data. The following work presents a context-aware authentication framework for Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communications, integrating Large Language Models (LLMs) with advanced cryptographic techniques. By leveraging real-time contextual data, the framework dynamically adapts authentication mechanisms to varying traffic conditions and potential security threats, reducing latency while enhancing accuracy. The proposed approach employs lightweight cryptographic protocols to ensure computational efficiency, making it suitable for resource-constrained vehicular environments. Comparative evaluations demonstrate that the framework outperforms existing authentication mechanisms in terms of security, scalability, and computational overhead. This solution contributes to the development of a more resilient and intelligent transportation system, addressing key challenges in autonomous vehicular networks. The significance of our results emphasises the necessity of a comprehensive strategy that includes organizational, governmental alongwith technological actions to protect the future of intelligent transportation systems. For different number of vehicles the service failure for 110 vehicles is 14.2%, communication cost is 2345 bytes and service endurance is 83.21%.