Deep-Learning-Based Mobile Group Intelligence Perception Mechanism Oriented to User Privacy and Data Security in the Internet of Things

Abstract

With the rapid development of the Internet of Things, a large number of mobile devices participate in the perception and aggregation of data, outsourcing and storing massive data on various cloud platforms. Thus, a new data perception and privacy protection model based on mobile group intelligence perception and cloud computing is required. The existing work on data security and privacy protection mainly focuses on the independent link of data collection, aggregation, and services, which lacks holistic consideration for the different service requirements. To end this issue, this article comprehensively integrates the security and privacy protection requirements of various stages in the mobile group intelligence perception for data collection, aggregation, and service from a global perspective. Aiming at data privacy and security issues in the existing mobile group intelligence perception system, and the difficulty in guaranteeing the quantity and quality of data at the same time, a mobile group intelligence perception mechanism oriented to user privacy and data security is proposed. This mechanism uses deep learning as its core algorithm to handle big data cases. It can provide authenticity and reliability guarantees for the subsequent data application on the premise of protecting user privacy. Experimental results prove that the mechanism proposed in this article meets the security requirements, and its user-end computing overhead is small.