On the Physical Layer Security of Federated Learning based IoMT Networks
Department
Computer Science
Document Type
Article
Publication Date
1-1-2022
Abstract
Internet of Medical Things (IoMT) connects different medical devices, health sensors and hospital records to data platforms using wireless communications. Federated Learning (FL) is an emerging collaborative learning technique that can be beneficial for IoMT due to reduced communication overhead and enhanced security. This paper provides an overview of different architectures used in FL and potential approaches for FL based IoMT. We also discuss how Physical Layer Security (PLS) can be used for efficient privacy preservation of data in FL based IoMT. We highlight the recent work in this area and major research challenges related to PLS assisted FL in IoMT. We also provide a case study demonstrating that clustering of IoMT devices (such that a single device in each cluster acts as a cluster head) enhances the secrecy rate of the FL based IoMT network as compared to its non-clustered counterpart. Finally, we also discuss future opportunities and open research questions related to PLS assisted FL in IoMT.
Journal Title
IEEE Journal of Biomedical and Health Informatics
Journal ISSN
21682194
Digital Object Identifier (DOI)
10.1109/JBHI.2022.3173947