Blockchain-enabled Federated Learning: A Survey

Federated learning (FL) has experienced a boom in recent years, which is jointly promoted by the prosperity of machine learning and Artificial Intelligence along with emerging privacy issues. In the FL paradigm, a central server and local end devices maintain the same model by exchanging model updates instead of raw data, with which the privacy of data stored on end devices is not directly revealed. In this way, the privacy violation caused by the growing collection of sensitive data can be mitigated. However, the performance of FL with a central server is reaching a bottleneck, while new threats are emerging simultaneously. There are various reasons, among which the most significant ones are centralized processing, data falsification, and lack of incentives. To accelerate the proliferation of FL, blockchain-enabled FL has attracted substantial attention from both academia and industry. A considerable number of novel solutions are devised to meet the emerging demands of diverse scenarios. Blockchain-enabled FL provides both theories and techniques to improve the performance of FL from various perspectives. In this survey, we will comprehensively summarize and evaluate existing variants of blockchain-enabled FL, identify the emerging challenges, and propose potentially promising research directions in this under-explored domain.

Automated summary

Federated Learning (FL), driven by the growth of machine learning and Artificial Intelligence as well as emerging privacy concerns, has gained popularity in recent years. FL allows a central server and local end devices to maintain the same model by exchanging model updates instead of raw data, thus protecting the privacy of sensitive data. However, the performance of FL with a central server is limited, and new threats are emerging. To accelerate the adoption of FL, blockchain-enabled FL has attracted attention as it provides theories and techniques to enhance FL performance. This survey aims to comprehensively summarize and evaluate existing blockchain-enabled FL variants, identify emerging challenges, and propose potential research directions in this under-explored field.