Digital Healthcare in the Metaverse: Insights into Privacy and Security
Mehdi Letafati, Safa Otoum
Abstract
In this article, metaverse healthcare systems are studied from the privacy and security perspectives. We address data communication security for the metaverse, and the privacy and security threats of employing machine learning and artificial intelligence (ML/AI) algorithms for metaverse healthcare. In addition, human-centric data privacy for the social interactions in the metaverse is studied. Our goal is to present new visions and approaches, including physical layer security, semantic metaverse communications, differential privacy, and adversarial machine learning. These approaches have shown promising results in the field of data communications and networking, as well as the computer science domain, showcasing a huge potential to be employed for the metaverse healthcare systems. As a case study, we propose distributed differential privacy for the metaverse healthcare systems, where each virtual clinic perturbs its medical model vector to safeguard privacy against malicious clients and honest-but-curious servers. Through our experiments on the Breast Cancer Wisconsin Dataset, we highlight the privacy-utility tradeoff for different adjustable levels of privacy.