A Differential Privacy Collaborative Deep Learning Algorithm in Pervasive Edge Computing Environment

With the development of 5G technology and intelligent terminals, the future direction of the Industrial Internet of Things (IIoT) evolution is Pervasive Edge Computing (PEC). In the pervasive edge computing environment, intelligent terminals can perform calculations and data processing. By migrating part of the original cloud computing model's calculations to intelligent terminals, the intelligent terminal can complete model training without uploading local data to a remote server. Pervasive edge computing solves the problem of data islands and is also successfully applied in scenarios such as vehicle interconnection and video surveillance. However, pervasive edge computing is facing great security problems. Suppose the remote server is honest but curious. In that case, it can still design algorithms for the intelligent terminal to execute and infer sensitive content such as their identity data and private pictures through the information returned by the intelligent terminal. In this paper, we research the problem of honest but curious remote servers infringing intelligent terminal privacy and propose a differential privacy collaborative deep learning algorithm in the pervasive edge computing environment. We use a Gaussian mechanism that meets the differential privacy guarantee to add noise on the first layer of the neural network to protect the data of the intelligent terminal and use analytical moments accountant technology to track the cumulative privacy loss. Experiments show that with the Gaussian mechanism, the training data of intelligent terminals can be protected reduction inaccuracy.

I. Introduction

With the Industrial Internet of Things (IIoT) development based on the Internet of Things platform, more and more devices have been connected to the Internet. How to use and utilize these massive data is an important research direction at present. Recently, 5G technology and intelligent terminals have improved communication and computing capabilities, and pervasive edge computing (PEC) has emerged. The pervasive edge computing model refers to a new type of computing model that performs calculations at the edge of the network and can migrate part of the original cloud computing model's calculations to intelligent terminals. For example, many cities now use cameras to take videos to analyze the situation of vehicles on various roads. Due to the large amount and sensitive data captured by video surveillance, uploading to the server will cause great communication pressure and security risks. In the pervasive edge computing environment, the intelligent camera processes the data locally after shooting the video, which greatly improves the overall efficiency and security of the system. Pervasive edge computing solves the problem that the General Data Protection Regulation (EU GDPR) restricts the company's collection of data from the intelligent terminal in a pervasive edge computing environment. However, in this mode, the information in the interaction between the intelligent terminal and the remote server still has the possibility of privacy leakage. How to protect this interactive information is a great challenge facing pervasive edge computing. With the extensive application of collaborative deep learning in the pervasive edge computing environment, protecting the privacy of its training data is an urgent problem to be solved.