Support vector machine user data prediction method based on multi-party secure computing protocol

Abstract

The invention discloses a support vector machine user data prediction method based on a multi-party secure computing protocol, which uses homomorphic encryption to encrypt user data, and solves the problem of insufficient prediction accuracy of an interference adding method by using the characteristic that the calculation result of a ciphertext can be consistent with the calculation result of a plaintext through the homomorphic encryption. The prediction accuracy of the support vector machine is improved; meanwhile, a third-party cloud server is introduced, and the multi-party secure computingprotocol is used for converting a computing process from a user and a prediction service party into the prediction service party and the third-party cloud server. The user simply needs to encrypt data and upload the encrypted data to the prediction service party, the user does not need to participate in the subsequent computing process, and whole-course networking is not needed. By utilizing themulti-party secure computing protocol, the computing process is simplified under the condition of protecting data privacy of the user and the support vector machine, and the computing efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of computing, and further relates to a support vector machine user data prediction method based on a multi-party secure computing protocol in the technical field of electrical digital data processing. The invention can be used in the machine learning prediction process based on the support vector machine, and realizes the protection of the safety of the user prediction data by encrypting the user data and performing multi-party security calculation, and is more efficient. Background technique [0002] Support vector machine is an algorithm in machine learning. With the maturity and development of machine learning technology, data mining under the combination of big data and machine learning has become more popular, from the e-commerce industry to the financial service industry, from the transportation industry To the medical and health industry, it has important applications from macro modeling to micro anal...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, and propose a support vector machine user data prediction method based on a multi-party secure computing protocol, which is used to solve the lack of accuracy of the prediction data in the prior art, and the user needs to participate in the calculation process , and the calculation process is more complex technical problems

Images