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

Data traffic privacy protection and recovery method and device based on tensor decomposition

A technology of tensor decomposition and privacy protection, which is applied in the field of privacy protection and recovery of data traffic based on tensor decomposition, can solve the difficulty of privacy protection and achieve the effect of maintaining data availability and satisfying privacy protection

Pending Publication Date: 2021-04-16
CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method of tensor decomposition has better recovery accuracy than matrix decomposition, but at the same time, it is more difficult to protect privacy
Therefore, there is no scheme that can combine the method of tensor decomposition and differential privacy, which can guarantee the privacy and efficiency of data at the same time.

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
  • Data traffic privacy protection and recovery method and device based on tensor decomposition
  • Data traffic privacy protection and recovery method and device based on tensor decomposition
  • Data traffic privacy protection and recovery method and device based on tensor decomposition

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example ；

[0047] refer to figure 1 , an embodiment of the present invention provides a data traffic privacy protection restoration method based on tensor decomposition, which is used for a trusted third-party server, comprising the following steps:

[0048] S101. The third-party server acquires the first and third order tensors sent by the client.

[0049] S102. The third-party server performs CP decomposition on the acquired first and third order tensors to obtain three factor matrices.

[0050] It should be noted that, in the embodiments of this paper, the CP decomposition of the third-order tensor is taken as an example for illustration. However, the embodiment herein is also applicable to the Tucker decomposition scheme, and those skilled in the art can fully apply this scheme to the Tucker decomposition scheme by taking CP decomposition as an example.

[0051] According to the above introduction, in steps S101 and S102 in this embodiment, a third-order tensor can be formed in the...

no. 2 example ；

[0097] refer to Figure 4 , an embodiment of the present invention provides a data flow privacy protection restoration method based on tensor decomposition, the method is used in a trusted third-party server, including the following steps:

[0098] S201. The third-party server acquires multiple information matrices sent by the client.

[0099] Among them, the information matrix is ​​the second-order tensor.

[0100] S202. The third-party server aggregates all the obtained information matrices to obtain the first and third order tensors.

[0101] S203. The third-party server performs CP decomposition on the first and third order tensors to obtain three factor matrices.

[0102] S204. The third-party server performs centralized differential privacy processing of the Gaussian mechanism on the factor matrix including the user's personal privacy.

[0103] S205. The third-party server reconstructs the factor matrix and the remaining factor matrix for differential privacy protecti...

no. 3 example ；

[0119] refer to Figure 6 to Figure 8 ( Figure 8 The middle dark color is the noise part), an embodiment of the present invention provides a data flow privacy protection recovery method based on tensor decomposition, which is used for a third-party server, including the following steps

[0120] S301. The third-party server receives multiple information matrices sent by the client; the information matrix is ​​obtained by the client through localized differential privacy processing under a random response mechanism;

[0121] S302. The third-party server aggregates the information matrix into a third-order tensor;

[0122] S303. The third-party server performs CP decomposition on the third-order tensor to obtain three factor matrices;

[0123] S304. The third-party server reconstructs the three factor matrices to obtain a new third-order tensor.

[0124] This method embodiment is based on the same inventive concept as the first embodiment and the second embodiment, that is, b...

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 data traffic privacy protection and recovery method and device based on tensor decomposition. Effective combination of tensor decomposition and differential privacy recovery tensor technology is realized, on one hand, a server receives a third-order tensor sent by a user side, decomposes the third-order tensor into a factor matrix, carries out differential privacy protection processing on the factor matrix containing user personal privacy, and finally reconstructs a new third-order tensor; and on the other hand, the server receives the localized differential privacy processing performed by the user side under the random response mechanism to obtain a plurality of information matrixes, the plurality of information matrixes are aggregated into a third-order matrix, and then tensor decomposition and reconstruction are performed. According to the method, tensor decomposition and differential privacy recovery tensor technologies are effectively combined, the generated three-order tensor data meet the privacy protection requirement, and the data availability is maintained to a certain extent.

Description

technical field [0001] The present invention relates to the technical field of data traffic privacy protection, in particular to a data traffic privacy protection recovery method and device based on tensor decomposition. Background technique [0002] Network flow data recovery refers to recovering the flow data at the next point in time by extracting the characteristics of the historical data of network flow data and analyzing them. At present, the new applications of the Internet of Things are developing rapidly, and the network flow data transported through 5G is gradually increasing. Therefore, how to quickly and effectively restore the network flow data is an urgent problem. [0003] Network flow data is a tensor with many parameters, including user's personal information, location, and time. Restoring network stream data has always been a very difficult problem, because such data has a large number of parameters and requires a huge amount of calculation. But at the sa...

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): G06F21/62G06F17/16
Inventor 王进韩惠何施茗王柳金彩燕
Owner CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY