EVALUATION OF PRIVACY-PRESERVING AI USING EDGE COMPUTING IN V2X FRAMEWORK

The advent of Vehicle-to-Everything (V2X) communication has ushered in a new era of intelligent urban transportation systems, promising enhanced safety, efficiency, and connectivity. However, the extensive data sharing inherent in V2X networks poses significant privacy challenges. This review paper explores the integration of privacy-preserving Artificial Intelligence (AI) within the V2X framework, emphasizing the role of edge computing as a pivotal enabler. We systematically examine state-of-the-art techniques in privacy-preserving AI, including federated learning, differential privacy, and homomorphic encryption, highlighting their applicability and effectiveness in V2X scenarios. Additionally, we discuss the synergy between edge computing and privacy preserving AI techniques, which collectively mitigate privacy risks while ensuring real-time data processing and decision-making. By analyzing current research trends, technological advancements, and practical implementations, this paper provides a comprehensive overview of the strategies for maintaining data privacy in V2X networks. Our findings underscore the importance of a holistic approach that combines robust privacy-preserving mechanisms with the decentralized capabilities of edge computing, paving the way for secure and efficient intelligent transportation systems