Federated Learning (FL) is a machine learning approach that enables training of AI models across decentralized devices or servers holding local data, ensuring privacy and security while collectively improving model performance.
Published in Chapter:
Intrusion Detection and Prevention Techniques in FL Cloud-Based Healthcare 5.0: A Comprehensive Review
Tarun Kumar Vashishth (School of Computer Science and Applications, IIMT University, India),
Vikas Sharma (School of Computer Science and Applications, IIMT University, India),
Kewal Krishan Sharma (School of Computer Science and Applications, IIMT University, India),
Bhupendra Kumar (School of Computer Science and Applications, IIMT University, India),
Sachin Chaudhary (School of Computer Science and Applications, IIMT University, India), and
Rajneesh Panwar (School of Computer Science and Applications, IIMT University, India)
Copyright: © 2024
|Pages: 23
DOI: 10.4018/979-8-3693-2639-8.ch010
Abstract
Federated learning (FL) in Cloud-based Healthcare 5.0 presents new opportunities for healthcare institutions to collaborate and leverage collective knowledge while ensuring data privacy and security. However, this collaborative and distributed nature also introduces new challenges in terms of intrusion detection and prevention. This chapter provides a comprehensive review of various intrusion detection and prevention techniques specifically tailored for FL Cloud-based Healthcare 5.0 environments. The abstract explores different approaches, including machine learning-based anomaly detection, blockchain technology for secure data sharing, real-time intrusion prevention at the edge, and threat intelligence sharing mechanisms. It analyzes the advantages and challenges associated with each technique and emphasizes the importance of ensuring regulatory compliance and safeguarding patient data. Additionally, the abstract addresses emerging technologies and federated cloud security frameworks to enhance intrusion detection and prevention in FL Cloud-based Healthcare 5.0.