Method and system for protecting data stream differential privacy based on edge calculation

Abstract

The invention discloses a method and a system for protecting data stream differential privacy based on an edge calculation. The method comprises the following steps: S1, receiving feature data by an edge device, wherein the data is collected by a terminal device and is extracted by a preset encoder; S2, aggregating the feature data and adding disturbance noise; and S3, performing feature reconstruction on the feature data after adding the disturbance noise by using a preset decoder to obtain reconstructed data. The encoder and the decoder are an encoder and a decoder which are obtained after training the same self-encoder. The method and the system for protecting data stream differential privacy based on the edge calculation have advantages that: service response delay is small, quality ofservice is high, system throughput is high, calculation load of each edge device is small, the amount of the data transmission between a user and the edge device is small, and the degree of privacy protection is high.

Description

technical field [0001] The present invention relates to the field of edge computing, and in particular to a data flow differential privacy protection method and system based on edge computing. Background technique [0002] With the advent of the information age, the information technology industry is developing rapidly. As one of the fastest-growing information technology industries, the Internet can provide users with diversified services and has become an indispensable part in various fields. With the increase of types and explosive growth of Internet terminal devices, as well as the significant growth of users' demand for Quality of Service (QoS) and diversification, the Internet is also facing many challenges today. Among them, how to deal with a large amount of data in the Internet, how to ensure the real-time service and how to ensure the security of users are the three main challenges. [0003] As a computing model based on the Internet, cloud computing provides on-...

AI Technical Summary

Problems solved by technology

[0007] 1. At present, even if edge computing enables part of the computing to be transferred from the cloud to the edge device close to the user, it still cannot meet the high real-time requirements of the service

[0008] 2. Edge computing is facing security issues, that is, the data processed by edge devices involves the contradiction between data availability and privacy security

[0009] 3. The centralized data cleaning (de-privacy) adopted by most privacy protection methods currently limits the system throughput and cannot meet the needs of low-latency services

[0010] 4. There is a contradiction between the computing capabilities of edge devices and security policies

Images