Fixed-point number coding and operation system for privacy protection machine learning

Abstract

The invention belongs to the technical field of network space safety, and particularly relates to a fixed-point number coding and operation system for privacy protection machine learning. The system comprises a fixed point number representation module, according to the fixed-point number encoding method, the fixed-point number encoding mode in the finite field is applied to privacy protection machine learning, the purpose of providing an overall solution of fixed-point number encoding and operation in privacy protection machine learning is achieved, and a fixed-point number encoding scheme andan operation mechanism in privacy protection machine learning are achieved. Compared with an existing machine learning framework, models (such as linear regression, logistic regression, a BP neural network and an LSTM neural network) trained by the machine learning framework for representing the fixed-point number through the system can execute prediction and classification tasks with almost thesame precision.

Description

technical field [0001] The invention belongs to the technical field of cyberspace security, and specifically relates to a fixed-point number coding and operation system for privacy protection machine learning. Background technique [0002] Machine learning has been widely used in their respective practical scenarios. For example, Internet companies collect massive amounts of user behavior data to train more accurate recommendation models. Hospitals collect health data to generate diagnostic models. Financial firms use historical transaction records to train more accurate fraud models. [0003] In machine learning, data size plays an important role in model accuracy. However, data distributed across multiple data sources or individuals cannot be easily combined. Regulations related to privacy issues such as GDPR, considerations for companies to maintain a competitive advantage and issues related to data sovereignty prevent data from being shared openly. Privacy-preservin...

AI Technical Summary

Problems solved by technology

[0010] 2. Know any k-1 copies or fewer of s i , will make S completely uncertain

[0029] The truncated coefficients of the product polynomial k(x) may not be completely random

Images