"Strengthening Data Privacy and Security for Internet of Vehicles using Federated Learning and Artificial Intelligence: A SLR"

"Federated Learning in the Internet of Vehicles space plays a crucial role in enabling intelligent, privacy-preserving, and distributed data processing. Here, AI models rely heavily on large-scale vehicle data for training and accuracy. While much of the existing research has focused on how Federated Learning can address computational, bandwidth, and infrastructure limitations\u2014especially by shifting model training to edge devices\u2014this study takes a different approach. It emphasizes the growing importance of data privacy protection, particularly as stricter data regulations emerge and organizations become increasingly hesitant to share sensitive data. This work presents a systematic literature review (SLR), analyzing the use of privacy-preserving and trust-enabling techniques within Federated Learning for IoV systems. Key methods examined include Homomorphic Encryption, Blockchain, Differential Privacy, Digital Twins, and incentive-based trust mechanisms. These technologies are designed to enhance privacy while enabling collaborative learning across distributed systems. The review\u2019s findings suggest that combining Federated Learning with advanced privacy methods is not only viable but necessary for building secure and trustworthy IoV ecosystems. As connected vehicles become more widespread, ensuring user trust and regulatory compliance will be essential. The study concludes by highlighting emerging trends and proposing future directions aimed at developing trust-centric Federated Learning frameworks tailored for the demands of next-generation intelligent transportation systems.Keywords: Federated Learning, Internet of Vehicles, IoV, encryption, data privacy, security, Intelligent Transportation Systems, homomorphic encryption, blockchain, digital twin, trust, differential privacy"