Multi-party joint model data processing method and device

Abstract

The embodiment of the invention provides a multi-party joint model data processing method and device for protecting data privacy. According to the method, after a model owner performs homomorphic encryption on k model parameters to obtain k parameter ciphertext, a first random number is selected to encrypt a random first message to obtain an auxiliary ciphertext; in addition, the model owner and adata owner jointly determine k challenge numbers. And then, the model owner combines the k challenge numbers with the model parameters and the first message, and the encrypted random number and the first random number to generate a verification random number and a verification message as zero knowledge proof. The data owner may verify whether a result of the homomorphic operation of the parametric ciphertext and the auxiliary ciphertext based on the k challenge number pairs is equal to a result of encrypting the verification message with the verification random number. And under the conditionof the same value, the homomorphic operation is carried out by using the sample characteristics, and the result is returned to the model owners, so that the security of private data of each party inthe model data process is ensured.

Description

technical field [0001] One or more embodiments of this specification relate to the field of machine learning and the field of data security, and in particular to a method and an apparatus for jointly processing model data by multiple parties. Background technique [0002] With the development of computer technology, machine learning has been applied to various technical fields to analyze and process various business data. The data needed for machine learning often involves multiple fields. For example, in the scenario of merchant classification analysis based on machine learning, the electronic payment platform has the transaction flow data of the merchants, the e-commerce platform stores the sales data of the merchants, and the banking institution owns the merchants. loan data. Data often exists in silos. Due to issues such as industry competition, data security, and user privacy, data integration faces great resistance. It is difficult to integrate data scattered across ...

AI Technical Summary

Problems solved by technology

When using the data processing model to process the sample feature data, if party A directly sends the sample data to party B, the feature value of the user sample will be exposed, leaking user privacy; if party B provides the data processing model to Party A's use will cause the model parameters of the data processing model to be exposed

Images