Federated Learning in Securing Edge Computing for Healthcare: A Cybersecurity Perspective

Abstract

With the increasing deployment of edge computing systems in various sectors, particularly in critical industries such as healthcare, manufacturing, and smart cities, the need for robust cybersecurity mechanisms has become more crucial than ever. Edge computing, which involves processing data locally on devices at the network's edge rather than sending it to centralized cloud servers, offers significant benefits in terms of reduced latency, enhanced privacy, and improved realtime decision-making. However, it also introduces unique security challenges, including data breaches, unauthorized access, and the vulnerability of distributed edge nodes. Federated learning (FL), a decentralized machine learning approach, has emerged as a promising solution for securing edge computing systems. By enabling collaborative model training across multiple edge devices without the need to share sensitive data, federated learning addresses privacy concerns while enhancing the overall security posture of edge networks. This paper explores the integration of federated learning into edge computing systems, focusing on its role in cybersecurity. It discusses the benefits, challenges, and potential use cases of federated learning in improving the resilience of edge networks against cyber threats, such as distributed denial-of-service (DDoS) attacks, data poisoning, and malicious insider threats. Additionally, the paper presents a case study demonstrating the practical application of federated learning in edge computing cybersecurity, highlighting its potential to provide scalable, privacy-preserving, and efficient security solutions.