Tackling Sybil Attacks in Intelligent connected vehicles: A Review of Machine Learning and Deep Learning Techniques

Intelligent connected vehicles (ICVs) have become increasingly prevalent in recent years, offering improved safety and efficiency. However, they are also vulnerable to various security threats, including Sybil attacks. This review paper provides a comprehensive overview of machine learning (ML) and deep learning (DL) techniques for detecting and preventing Sybil attacks in ICVs. We discuss traditional methods, as well as supervised, unsupervised, hybrid, and ensemble learning approaches. Furthermore, we analyze the challenges and limitations associated with implementing ML and DL techniques, such as data quality, computational resources, and real-time constraints. Despite these challenges, ML and DL hold significant potential for addressing Sybil attacks in this domain. Finally, we emphasize the importance of future research directions, including adaptive and transfer learning, federated learning, robustness to adversarial attacks, interpretability, and hybrid and ensemble approaches. This review aims to provide valuable insights for researchers and practitioners working on Sybil attack detection and prevention in ICVs.