Blockchain Assisted Federated Learning for Enabling Network Edge Intelligence

Abstract

The recently emerging federated learning (FL) exploits massive data stored at multiple user nodes to train a global optimal learning model without leaking the privacy of user data. However, it is still inadequate to learn the global model safely at the centralized aggregator, which is an essential part for the traditional FL architecture. Specifically, when using FL in radio access networks to enable edge intelligence, it is difficult for a central server, which belongs to a third party, to guarantee its credibility. Moreover, because the central server may cause a single point of failure, its reliability is also difficult to guarantee. Besides, a malicious participating node of FL may send ill parameters for model aggregation. In this article, we develop a blockchain assisted federated learning (BC-FL) framework, with aim to overcome the single point of failure caused by central server. Meanwhile, we propose to use blockchain to implement auditing of individual involved nodes to ensure the reliability of learning process. To avoid privacy leakage during the audit process to the greatest extent, we design a matching audit mechanism to realize efficient random matching audit process. A cryptocurrency free delegated byzantine fault tolerant (CF-DBFT) consensus mechanism is also designed to realize the low-latency distributed consensus of all nodes in the FL proces. We apply the proposed BC-FL framework to resolve the computing resource allocation problem at the edger servers in MEC network. Simulation results demonstrate the effectiveness and performance superiority of the proposed BC-FL framework. Compared with legacy FL algorithm, the serving time of MEC servers and utilization of computing resource are increased by 35% and 48% respectively under our proposed BC-FL algorithm.