Federated Learning: Balancing the Thin Line Between Data Intelligence and Privacy
This is an incremental survey paper that organizes existing knowledge about federated learning for researchers and practitioners.
This paper provides a systematic overview and taxonomy of federated learning, investigating security challenges like data poisoning and inference attacks while discussing training challenges such as non-i.i.d. data and heterogeneous architectures, with no concrete experimental results reported.
Federated learning holds great promise in learning from fragmented sensitive data and has revolutionized how machine learning models are trained. This article provides a systematic overview and detailed taxonomy of federated learning. We investigate the existing security challenges in federated learning and provide a comprehensive overview of established defense techniques for data poisoning, inference attacks, and model poisoning attacks. The work also presents an overview of current training challenges for federated learning, focusing on handling non-i.i.d. data, high dimensionality issues, and heterogeneous architecture, and discusses several solutions for the associated challenges. Finally, we discuss the remaining challenges in managing federated learning training and suggest focused research directions to address the open questions. Potential candidate areas for federated learning, including IoT ecosystem, healthcare applications, are discussed with a particular focus on banking and financial domains.