Practical Privacy-Preserving Federated Learning in Vehicular Fog Computing

Abstract

Benefitting from the outstanding capabilities of intelligent controlling and prediction, federated learning (FL) has been widely applied in Internet of Vehicle (IoV). However, applying FL into fog-computing-based IoV still suffers from two crucial problems: (i) how to achieve the privacy-preserving FL under the flexible architecture of fog computing with no assistance of cloud server, and (ii) how to guarantee the privacy-preserving FL to perform with high efficiency and low overhead in fog-computing settings. For addressing the above issues, we propose a practical framework, named <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Galaxy</small> , the first of its kind in the regime of privacy-preserving FL under the setting of non-cloud-assisted fog computing. Based on the secure multi-party computation (MPC) technology, our framework satisfies the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\boldsymbol{(T,N)}$</tex-math></inline-formula> -threshold property, permitting <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\boldsymbol{N}$</tex-math></inline-formula> (a scalable number) fog nodes to cooperate with multiple users for implementing privacy-preserving FL, while resisting the collusion up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\boldsymbol{T}-\boldsymbol{1}$</tex-math></inline-formula> fog nodes, and being robust to at most <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\boldsymbol{N}-\boldsymbol{T}$</tex-math></inline-formula> fog nodes simultaneously dropping out. Besides, considering the practical scenario that low-quality data may negatively impair the FL model convergence, our scheme can handle users’ low-quality data while protecting all user-related information under our secure framework. Based on the above superior properties, our scheme can perform with high scalability, high processing efficiency, and low resource overhead, being practical for fog-computing-based IoV. Extensive experiment results demonstrate our scheme with high-level performance.