FedVR360: Federated Learning enabled Privacy-Preservation for VR 360° Video Streaming in Vehicular Edge Computing

The integration of Virtual Reality (VR) 360° video streaming into Vehicular Edge Computing (VEC) enables immersive in-vehicle experiences but introduces significant challenges in privacy preservation and real-time performance. Existing predictive caching solutions rely on centralized learning, which requires aggregating sensitive user data such as head orientation and vehicle trajectories, thereby violating privacy regulations and exposing users to inference attacks. Federated Learning (FL) offers a promising solution; however, its deployment for VR streaming in VEC is constrained by highly non-Independent and Identically Distributed (non-IID) data, intermittent connectivity, and the need for joint multi-modal prediction without raw data exchange. To address these limitations, this paper proposes FedVR360, a comprehensive privacy-preserving FL framework for joint trajectory and viewport prediction in vehicular edge environments. The FedVR360 integrates a federated multi-modal Temporal Fusion Transformer with prototype-based cross-modal fusion, asynchronous hierarchical aggregation across vehicles and roadside units, and provides formal privacy guarantees using Rényi Differential Privacy. Additionally, a hybrid personalization strategy mitigates non-IID degradation. The performance evaluations conducted on real VR viewport traces and simulated vehicular trajectories show that FedVR360 achieves centralized performance by recovering over 84% of the centralized trajectory prediction gap and approximately 80% of the viewport prediction gap, while preserving strong privacy guarantees. Under a practical privacy budget, FedVR360 reduces membership inference attack success to near random guessing (50.5%) and significantly degrades the gradient inversion attacks. Across all evaluation metrics, FedVR360 achieves an F1@10 of 0.795 with corresponding improvements in precision and recall, reduces normalized trajectory prediction error to a mean absolute error of 0.282, maintains per-client prediction variance below 0.15 under non-IID data, and ensures real-time inference latency below 30 ms with moderate training and memory overhead, demonstrating a favorable balance between prediction accuracy, system efficiency, and formal privacy preservation.