A DISTRIBUTED MULTI-PARTY SECURITY MODEL TRAINING FRAMEWORK FOR PRIVACY PROTECTION BACKGROUND

摘要

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a multi-party secure logistic regression model (SLRM) by using secrete sharing (secret sharing) techniques. One of the methods includes dividing sample training data for a secure logistic regression model (SLRM) into a plurality of shares using secret sharing (SS), wherein each share is distributed to a secure computation node (SCN); iteratively updating parameters associated with the SLRM using each share of the sample training data, wherein the iterative updating continues until the occurrence of a predetermined condition; and after iteratively updating the parameters associated with the SLRM, outputting a training result configured for use by each SCN.