Federated Learning: Opportunities and Challenges

TL;DR

Federated Learning enables collaborative model training across devices without sharing private data, offering privacy benefits but facing security challenges, with significant potential in sensitive sectors like healthcare and finance.

Contribution

This paper reviews the opportunities and challenges in federated learning, highlighting its potential and vulnerabilities in privacy-sensitive applications.

Findings

FL preserves data privacy in collaborative learning

FL faces security vulnerabilities such as attacks

Opportunities in healthcare and finance sectors

Abstract

Federated Learning (FL) is a concept first introduced by Google in 2016, in which multiple devices collaboratively learn a machine learning model without sharing their private data under the supervision of a central server. This offers ample opportunities in critical domains such as healthcare, finance etc, where it is risky to share private user information to other organisations or devices. While FL appears to be a promising Machine Learning (ML) technique to keep the local data private, it is also vulnerable to attacks like other ML models. Given the growing interest in the FL domain, this report discusses the opportunities and challenges in federated learning.