A privacy-preserving multi-institutional data classification method based on homomorphic encryption

Abstract

The invention discloses a privacy protection multi-institutional data classification method based on homomorphic encryption. Firstly, the screening conditions of the training data generated by the user are sent to the computing center; ; Each data provider screens the local data marked with classification labels to obtain training data, generates their own public key and private key using the homomorphic encryption algorithm according to the encryption parameters, and sends the training data to the computing center through public key encryption; The center and various data providers jointly perform logistic regression analysis under homomorphic encryption, and the data classification model is obtained and sent to the user; the user inputs the data to be classified into the data classification model to obtain the classification result. The present invention has higher security in practical application, not only effectively protects personal privacy, but also avoids possible loss of interests of data providing institutions, and greatly promotes the development of multi-institutional data analysis.

Description

technical field [0001] The invention belongs to the technical field of multi-institutional data analysis, and in particular relates to a privacy-protecting multi-institutional data classification method based on homomorphic encryption. Background technique [0002] Currently, most data analysis research is conducted on limited datasets from a single institution. However, such an approach has significant limitations. On the one hand, for some specific research, a single institution may not be able to generate enough supporting data, for example, for a rare disease, a single medical institution usually cannot provide enough data; on the other hand, due to the limitations of various observation techniques With the development, more and more heterogeneous data have been generated, which also poses more challenges to data mining. For example, the research by Joshua C Denny, a scientist at Vanderbilt University in 2013, showed that in a single medical institution's electronic Ge...

AI Technical Summary

Problems solved by technology

On the one hand, through proper processing of these exposed information, some sensitive information can be deduced, leading to the disclosure of personal privacy

On the other hand, data itself has value, and a large amount of exposed information may be maliciously used by third parties without authorization, resulting in the loss of interests of data providers

This significantly hampers multi-institutional data analysis

Images