Abstract: Recent advancements in emerging technologies, like artificial intelligence (AI) and the Internet of Health Things (IoHT), have propelled a remarkable revolution in smart healthcare. However, traditional AI approaches that rely on centralized data collection and processing have proven impractical and unattainable in healthcare due to expanding network scale and escalating privacy concerns. Federated Learning (FL), an emerging distributed and collaborative technique, appears as a potential solution to address the security and privacy challenges associated with conventional AI. By enabling the training of machine learning (ML) models on decentralized data stored across diverse wearable devices, including fitness trackers, smartwatches, implantable devices, and other IoHT devices, FL facilitates the analysis and interpretation of data while upholding the security and privacy of the participating devices and raw data. Accordingly, this comprehensive study reviews the different FL techniques aimed at bolstering security and privacy in modern digital healthcare systems. Moreover, it highlights the benefits and challenges of FL in healthcare and presents future research trends aimed at enhancing the cybersecurity posture of FL in modern healthcare systems.
Taylor and Francis, Artificial Intelligence Solutions for Cyber-Physical Systems, 2024
Adam A. Alli, Kassim Kalinaki, Mugigayi Fahadi, Lwembawo Ibrahim
IET, Cybersecurity in Emerging Healthcare Systems, 2024
Kassim Kalinaki, Rufai Yusuf Zakari, Wasswa Shafik
IGI Global, Intersection of AI and Business Intelligence in Data-Driven Decision-Making, 2024
Ahmad Fathan Hidayatullah, Kassim Kalinaki, Haji Gul, Rufai Zakari Yusuf, Wasswa Shafik
IGI Global, Intersection of AI and Business Intelligence in Data-Driven Decision-Making, 2024
Kassim Kalinaki