Privacy protection data processing method, device and equipment and machine learning system

Abstract

The invention provides a privacy protection data processing method, device and equipment and a machine learning system. In one embodiment of the method, when a data processing result of a non-linear activation function used in a machine learning algorithm needs to be obtained in a multi-party participated data sharing application scene, a lossless expression of the non-linear activation function can be used, each subitem can be cooperatively calculated by utilizing multi-party security calculation, the subitem can be prevented from being expanded into an approximate evaluation algorithm of a polynomial, the calculation complexity is reduced, and the data processing efficiency of the non-linear activation function calculated by computer equipment is improved. Moreover, the complexity and precision loss of approximate calculation of nonlinear activation functions such as Taylor expansion can be greatly reduced.

Description

technical field [0001] The embodiments of this specification belong to the technical field of privacy protection in cryptography, and in particular relate to a data processing method, device, equipment and machine learning system for privacy protection. Background technique [0002] Machine learning models can include activation functions. The activation function in some machine learning models is a transcendental function (such as a Sigmoid function), and the operations involved in the transcendental function usually include nonlinear operations such as exponential operations and trigonometric operations. When the computer processes these nonlinear activation function data, it usually uses the calculation method of Taylor expansion. The calculation data is exponential, and the calculation process is relatively complicated. [0003] In the current multi-party data sharing application scenarios, it is often necessary for multiple participants to collaborate to jointly establ...

AI Technical Summary

Problems solved by technology

When the computer processes these nonlinear activation function data, it usually uses the calculation method of Taylor expansion. The calculation data is exponential, and the calculation process is relatively complicated.

Images