Defending Against Malicious Behaviors in Federated Learning with Blockchain

arXiv:2307.00543v2 Announce Type: replace-cross
Abstract: In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owners, or clients, to collaboratively train machine learning models without compromising data privacy. However, most existing FL approaches rely on a centralized server for global model aggregation, leading to a single point of failure. This makes the system vulnerable to malicious attacks when dealing with dishonest clients. In this work, we address this problem by proposing a secure …

aggregation arxiv blockchain clients cs.ai cs.cr cs.gt cs.lg data data privacy deep learning defending federated federated learning global machine machine learning machine learning models malicious privacy server train