Federated Machine Learning in 5G Smart Healthcare: A Security Perspective Review

Hira Akhtar Butt, Abdul Ahad, Muhammad Wasim, Ibraheem Shayea, Paulo Jorge Coelho*, Ivan Miguel Pires, Nuno M. Garcia

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

3 Citations (Scopus)

Abstract

Federated learning (also known as collaborative learning) is a decentralized approach to training machine learning models. In 5G smart healthcare, federated machine learning (FML) can potentially improve patient care by offering improved diagnosis, prognosis, and therapy models. Nevertheless, a significant worry regarding FML is its lack of security. Within the context of 5G smart healthcare, this review paper looks at FML from a security point of view, discussing the benefits and risks of using FML in 5G smart healthcare and the possible solutions to these risks. The issues of privacy, adversarial attacks, communication security, and malevolent clients are brought up in the discussion on security challenges. Differential privacy, secure aggregation and training, adversarial training, secure communication, client authentication, and model pruning are some of the solutions that have been suggested. We will be able to protect the privacy of patient data in FML if we take the necessary steps to address these security problems.

Bibliographical note

Publisher Copyright:
© 2023 Elsevier B.V.. All rights reserved.

Keywords

  • 5G
  • Federated machine learning
  • Healthcare
  • Security

Fingerprint

Dive into the research topics of 'Federated Machine Learning in 5G Smart Healthcare: A Security Perspective Review'. Together they form a unique fingerprint.

Cite this