Author:
Kenioua Laid,Lejdel Brahim,Abdelhamid Nedioui Mohamed
Abstract
The emergence of Autonomous Vehicles (AVs) marks a significant turning point in the future of transportation and reflects radical advancements in artificial intelligence, edge computing, advanced sensing systems, and advanced control. These vehicles have sophisticated sensors, artificial intelligence systems, and computing capabilities that enable them to drive and operate without human intervention. They rely on various technologies such as cameras, radar, and GPS to obtain precise information about their surroundings and make real-time decisions. However, AVs face several unique challenges. They depend on accurate and reliable location information to drive and operate, ensuring safe driving and real-time decision-making. One of the major challenges is that central positioning systems are vulnerable to attacks, security breaches, spoofing attacks, and signal jamming, which can tamper with vehicle command systems. The significance of accurately determining the vehicle’s location lies in improving driving precision, efficient decision-making, enhanced mobility in different environments, and ensuring constant communication among vehicles for better collective performance. In this research, we propose an engineering model based on mixed collaboration for secure measurement in autonomous vehicle positioning. This collaboration enhances cooperation among vehicles, where the leader obtains its location through satellite identification, and the rest of the group members depend on the leader’s location to determine their positions in a highly reliable and immune manner against GPS spoofing, signal jamming, and fraudulent attacks. Additionally, to ensure secure communication among different vehicles, a strong encryption system has been adopted to send messages within the proposed framework, ensuring higher reliability. The technique used is lightweight and robust because it uses only one operation of multiplication and only one exponential operation. Moreover, network traffic analysis and the complexity of different algorithms have been assessed to ensure the efficiency and effectiveness of the proposed framework.