Method for performing security statistical analysis by using fully homomorphic encryption in cloud computing environment

Abstract

The invention provides a method for carrying out security statistical analysis by using fully homomorphic encryption in a cloud computing environment, relates to the technical field of cloud computing information security, and solves the problem of how to carry out statistical calculation and ensure data calculation precision under the condition that a cloud end is not credible during calculation outsourcing. On the basis of a three-party system formed by a local, a user client and a cloud server, firstly, the user client participating in security statistical analysis is determined, and from the perspective of privacy protection, homomorphic encryption is carried out on statistical data of the user client based on a multiplication protocol, an addition protocol and an integer comparison protocol of fully homomorphic encryption, data are encrypted and uploaded to a cloud server, the data in a ciphertext state is directly calculated in a cloud environment, calculation is completed under the condition that privacy is not leaked, corresponding statistic analysis, statistic result inspection and unary linear regression fitting are obtained, real calculation outsourcing is achieved, and the calculation precision is guaranteed based on the fully homomorphic encryption technology.

Description

technical field [0001] The present invention relates to the technical field of cloud computing information security, and more specifically, relates to a method for security statistical analysis using fully homomorphic encryption in a cloud computing environment. Background technique [0002] In recent years, with the influx of massive data and the development of the times, various businesses require more data storage space and stronger data processing capabilities. In terms of data processing, a single computing engine can no longer meet the needs of users. Cloud computing and big data technology emerged as the times require. With the rapid development of cloud computing and big data technology, the storage space and computing power of cloud servers make it possible to perform data mining and statistical processing in the cloud, but how to ensure The privacy and security of users has become the primary issue in its promotion and application. [0003] In order to prevent dat...

AI Technical Summary

Problems solved by technology

[0002]In recent years, with the influx of massive data and the development of the times, various businesses require more data storage space and stronger data processing capabilities. In terms of data processing, a single computing engine can no longer meet the needs of users, and cloud computing and big data technology have emerged as the times require. With the rapid development of cloud computing and big data technology, the storage space and computing power of cloud servers make data processing in the cloud Mining and statistical processing become possible, but how to ensure the privacy and security of users under the cloud service model has become the primary problem in its promotion and application

[0003] In order to prevent data leakage, encrypting data and then storing it on a cloud platform is recognized as the most effective method, but this brings a new problem: The encrypted ciphertext has no characteristics, and the cloud platform cannot effectively process it, losing its advantages in big data processing. Once the data is decrypted, it is very easy to cause privacy data leakage, and even bring serious catastrophic consequences. , in the process of data mining and statistical analysis in the cloud, it is necessary to ensure the privacy of the data, but also to ensure its accuracy. As a key means to solve this problem, the fully homomorphic encryption technology is a Encryption algorithms that operate but can still restore plaintext, such as a Chinese patent (publication number: CN109327304A) on February 12, 2019, disclosed a lightweight homomorphic encryption method for privacy protection in cloud computing. The calculation is realized under the cloud environment, which effectively solves the problem of data uploading to the server in the cloud environment, and the cloud is not trustworthy. However, while ensuring privacy, the data cannot be statistically analyzed, so the accuracy of the calculation results cannot be determined, and the accuracy of the data calculation cannot be guaranteed.

Images