Intelligent privacy preserving deep learning model for securing IoT healthcare system in cloud storage

Abstract

Nowadays the existing legacy management-based healthcare system maintains and processes a large amount of health-related data. The widespread adoption of the Internet of Things (IoT) and its progressive development have promised the way for the development of IoT-enabled healthcare with impressive data processing and big data storage capabilities. Intelligent medical healthcare intends to offer a framework to remotely monitor users’ health-related data as the Industrial Internet of Things (IIoT) develops. Because they are stored on a cloud server, the data are still susceptible to manipulation and privacy breaches. The Keras Xception Deep Learning System (KX-DLS) with Dynamic Searchable Symmetric Encryption (DSSE) scheme is a revolutionary IoT-based deep learning intelligent privacy-preserving system that is advantageous for digital healthcare and its functionalities to handle security-related challenges. The dataset is being used to pre-train the system, and users’ personal information is kept separate in a secure location. Without knowing any personal information about the users, we analyse health-related data stored in the cloud and build a sophisticated security framework based on a deep learning model. With the most extensive collection of security features, our framework for learning intelligent privacy preservation optimizes the system to guarantee high data integrity and few privacy breaches. As a result, it may be useful in situations where users employ mobile devices with limited resources to engage a healthcare cloud system for extensive virtual health services, and the results of this research show that it has been a better-secured model in comparison with state-of-the-art previous techniques.