Method for defending graph data attack by using differential privacy technology

A technology of differential privacy and graph data, which is applied in the fields of electrical digital data processing, biological neural network models, instruments, etc., to achieve the effect of convenient deployment and weakened attack effect

Pending Publication Date: 2021-07-30
UNIV OF SCI & TECH OF CHINA
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0019] At present, the defense effect of various attacks against the GNN model needs to be improved, so it is necessary to develop a new defense scheme

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
  • Method for defending graph data attack by using differential privacy technology
  • Method for defending graph data attack by using differential privacy technology
  • Method for defending graph data attack by using differential privacy technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0062] The preferred implementation method of this step is as follows:

[0063] First, the server side processes the received node characteristic data, the formula is:

[0064]

[0065] in, is the node feature data processed locally by the LDP algorithm, x′ u is the unbiased estimation result of the server on the node features, d is the dimension of the node features, m is the dimension that needs to be disturbed in the node features, each dimension of the node features is in the interval [α, β], α, β is the lower limit and upper limit of the set interval respectively; ∈ is the privacy budget selected by the server, and e is a natural constant.

[0066] The above processing is an unbiased estimation of node characteristics, and the availability of data can be maintained through the above processing.

[0067] Afterwards, differential privacy processing is performed on the edge of the node, specifically by performing differential processing on the adjacency matrix of edge...

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 method for defending graph data attack by using a differential privacy technology, which comprises the following steps of: for a graph model to be protected, collecting original graph data in the graph model; carrying out unbiased estimation processing on the original image data by adopting a differential privacy technology; and training a graph model by utilizing the processed graph data to obtain the graph model with the capability of defending the attack of the graph data. According to the method, on one hand, the communication overhead between the server and the user is not increased, deployment is convenient in an actual scene, and extra hardware facilities are not needed; and on the other hand, the accuracy of the original task of the model is basically not influenced, and meanwhile, the attack effect can be weakened.

Description

technical field [0001] The present invention relates to the technical field of graph data attack defense, in particular to a method for using differential privacy technology to defend against graph data attacks. Background technique [0002] In recent years, artificial intelligence has set off wave after wave, and AI has gradually entered all aspects of people's lives. While chasing AI, one thing is overlooked, AI is fed by data, and it is a large amount of high-quality data. In real life, except for a few giant companies that can meet the requirements, most enterprises have the problem of small amount of data and poor data quality, which is not enough to support the realization of artificial intelligence technology; at the same time, domestic and foreign regulatory environments are gradually strengthening data protection, and successively introduced Therefore, the free flow of data under the premise of security and compliance has become the general trend; from the perspect...

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): G06F21/55G06N3/04
CPCG06F21/554G06N3/045
Inventor 程绍银杜文涛孙启彬
Owner UNIV OF SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap