Autonomous vehicles (AVs) represent a technology with significant social and environmental benefits. By reducing dependence on the human factor, which is responsible for 94% of the 1.35 million annual traffic deaths globally, AVs have the potential to increase road safety and save lives. Complementary technologies, such as Vehicle-to-Everything (V2X) communication, further enhance traffic management, reducing congestion by up to 40% and improving energy efficiency with fuel savings of up to 15%. However, V2X systems are particularly vulnerable to cyber attacks, such as spoofing, which injects false information, disrupting the flow of traffic and compromising the safety of AVs. This paper proposes an innovative framework for detecting and mitigating spoofing attacks in V2X communications. The solution combines Direction of Arrival (DoA) estimation with advanced object detection algorithms, such as YOLOv8, to identify anomalous signals and locate malicious transmitters. By integrating Artificial Intelligence (AI) techniques, the framework makes it possible to accurately classify attackers and select customized countermeasures, ensuring greater network reliability and security. The simulation results demonstrate the framework’s effectiveness in various dynamic scenarios using data from antenna arrays and camera-based object detection. In addition, they highlight the importance of sensor data fusion to improve anomaly detection accuracy, optimize decision-making processes in AVs, and enable robust cross-validation of transmitted information.
Silva et al. (Thu,) studied this question.