Model updating method, device and equipment

Abstract

The invention discloses a model updating method, device and equipment. According to the scheme provided by the embodiment of the invention, the method includes under the condition that a shadow set Sand a target sample are given, respectively calculating prior probabilities alpha of training samples contained in the shadow set; and sampling according to the shadow set S, and training the samplingtraining parameter distribution of the sampling model obtained when the model is trained, calculating the posterior probability P of the target sample z in the shadow set according to the training parameter distribution of the given model and the characteristic value of the target sample; evaluating whether the privacy leakage degree of the trained model for the training sample set is qualified or not according to the difference value of the posterior probability P and the prior probability alpha; and if not, changing the affiliation relationship between the target sample and the training sample set, thereby obtaining a new training sample set and performing model adjustment to avoid privacy data leakage.

Description

technical field [0001] The embodiments of this specification relate to the field of information technology, and in particular, to a model updating method, device, and equipment. Background technique [0002] In the process of machine learning, machine learning model algorithms based on data training often face the problem of leaking user privacy in training data. For example, in a membership attack against a model, the attacker of the membership attack is given a trained model and one or more specific samples, trying to determine whether the sample is used in training the model, In order to reversely try to derive the training method and recognition method of the model. [0003] Based on this, a model update scheme that can avoid privacy leakage in machine learning is needed. Contents of the invention [0004] The purpose of the embodiments of the present application is to provide a model update scheme that can avoid privacy leakage in machine learning. [0005] In orde...

AI Technical Summary

Problems solved by technology

[0002] In the process of machine learning, machine learning model algorithms based on data training often face the problem of leaking user privacy in training data

Images