Privacy Enhanced Authentication for Online Learning Healthcare Systems

The widespread application of Internet of Things technology in the medical field results in the generation of a large amount of healthcare data. Adequately learning valuable knowledge from the massive healthcare data brings a huge potential for improving the efficiency, quality, and safety of healthcare services. Online learning over the cloud offers decent training and fast inference services. However, outsourcing healthcare data learning to the cloud might cause patient privacy disclosure and data integrity and authenticity compromises. These security threats further affect the accuracy of the trained model or distort the inference results. Although researchers have tried to solve the privacy-preserving or data integrity issues with different techniques, none of them satisfy the security demands in online training of healthcare data. In this paper, we present an efficient redactable group signature scheme (RGSS) for the online learning healthcare system. The security analysis shows that our construction not only prevents privacy compromise but also provides integrity and authenticity verification. In addition to the private property of RGSS, the signer-anonymous also enhances patient privacy-preserving. Compared with other solutions, our RGSS is secure and efficient in promoting scientific research on learning large amounts of healthcare data that aim to improve healthcare services.