I. Introduction
The smartphone contains Personal Health Records (PHR) comprising data (i.e., family medical histories, past medical and surgical interventions, mental health data, physical activity data, heart rate data, and mood prediction) [1]–[3]. Studies [4]–[6] have shown that PHR data can be stolen using a smartphone’s hardware sensor. Regulatory requirements (i.e., General Data Protection Regulation (GDPR) [7], HIPAA [8]) can be met with the help of a newly emerging paradigm, Federated learning (FL), in the field of machine learning. While making use of benefits associated with massively distributed data, FL can mitigate privacy concerns [9]–[12]. FL helps the participants in collaborative training of a global model without sharing their local training data [12]. During each round of communication, all participants train local models based on their training data, and the model is then submitted to the server with updates. A global model is built by the server while employing a secure aggregation using the average of weights associated with local models [13], [14].