Data privacy protection system based on secure two-party calculation linear regression algorithm

Abstract

The invention discloses a linear regression algorithm based on secure two-party calculation. The method comprises the following steps: S1, adopting multiplication of a secret sharing value; S2, preprocessing the training data; S3, initializing parameters; S4, updating model parameters; S5, preprocessing the prediction data; S6, calculating a prediction sharing value; and S7, reconstructing a prediction result. According to the scheme, the privacy of data and model parameters is not leaked, and meanwhile, the required communication overhead is lower. According to the method, privatization is carried out on original training data and model parameters, and a linear regression algorithm for protecting data privacy is realized by virtue of convenience of cloud service under the condition that acloud server cannot obtain the original training data and intermediate parameters and cannot deduce the model parameters. On the basis, a regression prediction task can be safely executed, and when computing and storing resources of the cloud server are utilized, training and data prediction of a linear regression model can be efficiently and accurately carried out.

Description

technical field [0001] The invention relates to the private field of information security technology, in particular to a data privacy protection system based on a secure two-party calculation linear regression algorithm. Background technique [0002] Linear regression (Linear Regression) is a method of modeling the relationship between one or more independent variables and dependent variables with a linear model. Its core idea is to fit a series of influencing factors and results to outline the relationship between the dependent variable Correlation among independent variables. As a classic algorithm, it is widely used in the field of statistical analysis and machine learning. In order to describe the optimal linear regression model, it is often necessary to provide a large amount of raw data from different data providers and send them to the cloud server for centralized training. However, cloud servers are often untrustworthy or even malicious, so research on how to avoid ...

AI Technical Summary

Problems solved by technology

Since the current secure multi-party computing scheme applied to machine learning needs some other cryptographic techniques (such as oblivious transfer protocol, homomorphic encryption, etc.), its main challenge is how to build a secure and efficient computing protocol through multiple parties.

[0005] In 2011, Hall et al. first proposed a secure two-party computing linear regression protocol based on homomorphic encryption, but it relied too much on homomorphic encryption with huge computational overhead, and this scheme could not be applied to data with huge data entries. concentrated

[0006] In summary, the traditional data privacy-preserving linear regression algorithm is usually based on the oblivious transfer protocol. Due to the high communication complexity of the oblivious transfer protocol and the computational limitations of homomorphic encryption, the efficiency in the regression task is not high.

Images