Privacy protection machine learning reasoning method and system based on secure multi-party computing

Abstract

The invention belongs to the field of data security and the technical field of cryptography application, and discloses a privacy protection machine learning reasoning method and system based on secure multi-party computation.The privacy protection machine learning reasoning method based on secure multi-party computation.The privacy protection machine learning reasoning method based on secure multi-party computationcomprises the steps that a service provider commits a machine learning model provided by the service provider; generating a label to ensure one-to-one binding of the label and the model; the model is limited by using the label to ensure that the model is not changed after the user selects the label; before a user starts machine learning reasoning, verifying whether the selected label is changed or not by using zero-knowledge proof; and finally, the security of the calculation process is ensured by using a security calculation framework. According to the method, the characteristics that the commitment cannot be changed and zero knowledge proves zero knowledge are fully utilized, no trusted third party participates in the whole service process, that is, no third party masters the data of both parties at the same time, and the problem that the third party is not trusted is fundamentally solved.

Description

technical field [0001] The invention belongs to the field of data security and the field of cryptography application technology, and in particular relates to a privacy protection machine learning reasoning method and system based on secure multi-party computing. Background technique [0002] At present, in the information age, life is inseparable from data. In order to process these data more conveniently, the method of using machine learning to process data has emerged. The machine learning method is a method in which a computer uses existing data to obtain a certain model and uses this model to predict the future. As a mainstream data processing scheme, it plays an important role in many fields. With the continuous promotion of machine learning algorithms, the accuracy of machine learning reasoning has been continuously improved, and the cost has been continuously reduced. Not only enterprises, but also many individuals want to process their own data through machine learn...

AI Technical Summary

Problems solved by technology

However, the publicly verifiable performance of secure multi-party computation is low, and the high complexity of hash circuits will bring large computational overhead

[0003] Through the above analysis, the existing problems and defects of the existing technology are: the publicly verifiable performance of secure multi-party computation in the existing technology is low, and the high complexity of the hash circuit will bring large computing overhead

Images