A Comparative Analysis of Federated Learning and Privacy-Preserving Techniques in Healthcare AI

Abstract

AI might conduct screening and assessment in the event that medical expertise is lacking in a setting with limited resources. Because algorithms are involved, even the most rapid AI decisions are methodical in comparison with human decision-making. In this chapter, the authors provide a thorough literature review on data privacy for healthcare AI system development. In order to facilitate safer translational AI research, they offer a comprehensive review of the privacy issues data owners have when sharing datasets with researchers. They go over the many forms of attacks and how they might jeopardize user privacy. They also go into detail about several possible ways to fix these privacy problems.

Ähnliche Arbeiten