Unlock instant, AI-driven research and patent intelligence for your innovation.

Domain adaptive privacy protection method based on differential privacy for deep neural network

A deep neural network and differential privacy technology, applied in the field of artificial intelligence security, can solve problems such as a large amount of time and energy, and difficult classification of models, achieving low actual loss, strong practicality, and the effect of protecting personal privacy

Active Publication Date: 2020-05-01
WUHAN UNIV
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in order to achieve good performance, deep learning requires a lot of data to train the model, which usually requires a lot of time and effort
The difference in data sets also makes it difficult for a trained model to directly classify another data set

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Domain adaptive privacy protection method based on differential privacy for deep neural network
  • Domain adaptive privacy protection method based on differential privacy for deep neural network
  • Domain adaptive privacy protection method based on differential privacy for deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] As shown in the figure, the differential privacy-based domain adaptive privacy protection method designed for deep neural networks in the present invention includes the following steps:

[0038] 1) if figure 1 As shown in , a deep feed-forward neural network model with two processes is defined for the server with the image in the source domain and the user with the image in the target domain. In process 1, the model is trained to predict the label of the source domain image, where the source domain image label is known. In process 2, the model is trained to predict the labels of source domain images and target domain images, where the source domain image label is defined as 1 and the target domain image label is defined as 0.

[0039] 2) if figure 1As shown, this model can be decomposed into three parts, feature extraction part, label prediction part and domain classification part. The data in both stages will be mapped in the feature extraction part. This model use...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a domain adaptive privacy protection method based on differential privacy for a deep neural network. A novel deep network framework is provided, and data privacy can be protected while a domain adaptation technology is realized. In the real scene of transfer learning, such as schools and hospitals, a training data set is generally private, and a scheme for flexibly protecting domain adaptation technical privacy does not exist nowadays, so that the method has very strong practicability. According to the method, domain adaptation training is carried out by using the ideaof adversarial learning, and privacy protection is carried out on the domain adaptation training process through differential privacy for the first time. Experimental results show that the model can complete domain adaptation tasks with ideal accuracy under proper privacy consumption.

Description

technical field [0001] The invention relates to a domain-adaptive privacy protection method based on differential privacy oriented to a deep neural network, and belongs to the field of artificial intelligence security. Background technique [0002] Deep learning has demonstrated great capabilities in solving many problems, such as speech recognition and computer vision. But in order to achieve good performance, deep learning requires a lot of data to train the model, which usually requires a lot of time and effort. The difference in data sets also makes it difficult for a trained model to directly classify another data set. These requirements have promoted the development of transfer learning, which can transfer the model trained on the source domain and use it to classify the target domain data. Domain adaptation techniques are one way to achieve transfer learning. [0003] Specifically, the domain adaptation technique aims to map the source domain data and the target do...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/08
CPCG06N3/08
Inventor 王骞李子希赵令辰邹勤
Owner WUHAN UNIV