Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
TRAINING METHOD AND DEVICE FOR NEURAL NETWORK MODEL FOR PROTECTING PRIVACY AND SECURITY
Document Type and Number:
WIPO Patent Application WO/2021/098255
Kind Code:
A1
Abstract:
Provided in the embodiments of the present description are a training method and device for a neural network model for protecting privacy and security. The method comprises: acquiring a preliminarily trained target neural network model and a training dataset, the target neutral network model comprising multiple intermediary layers, the training dataset comprising a first number of member samples; determining a decision-making critical layer and a decision-making irrelevant layer, the degree of influence of the decision-making critical layer on a decision result being greater than the degree of influence of the decision-making irrelevant layer on the decision result; retraining the target neural network model on the basis of the member samples in the training dataset, the retraining fixing a parameter of the decision-making irrelevant layer of the target neural network model, thus allowing some neurons of the decision-making critical layer to stop working at a certain probability so as to adjust a parameter of the decision-making critical layer. This prevents an attacker from detecting training data of the neural network model.

Inventors:
WENG HAIQIN (CN)
Application Number:
PCT/CN2020/103605
Publication Date:
May 27, 2021
Filing Date:
July 22, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
ALIPAY HANGZHOU INF TECH CO LTD (CN)
International Classes:
G06F21/55
Foreign References:
CN110874471A2020-03-10
CN108776836A2018-11-09
CN104504441A2015-04-08
CN107368752A2017-11-21
US20170024642A12017-01-26
Attorney, Agent or Firm:
BEIJING BESTIPR INTELLECTUAL PROPERTY LAW CORPORATION (CN)
Download PDF: