Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Network structure deanonymization system and method based on matrix decomposition

A network structure and matrix decomposition technology, applied in transmission systems, digital transmission systems, data exchange networks, etc., can solve problems such as limited accuracy, global structural information is not widely used, etc., to prevent inference attacks.

Active Publication Date: 2020-03-27
CHONGQING UNIV OF POSTS & TELECOMM
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the existing network structure deanonymization methods are only based on the anonymous network, and the accuracy is limited, and most of the existing network structure deanonymization methods are only based on the local structure of network nodes to infer sensitive relations, and the global structure information has not been widely used. use

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
  • Network structure deanonymization system and method based on matrix decomposition
  • Network structure deanonymization system and method based on matrix decomposition
  • Network structure deanonymization system and method based on matrix decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] In this embodiment, the present invention proposes a network structure deanonymization system based on matrix decomposition, including a dynamic network acquisition data module, a low-rank sparse model training module, a non-negative matrix decomposition training model building module, an optimization module, in:

[0045] The dynamic network-static network conversion module is used to obtain the adjacency matrix of the static network and the static network according to the social network data of the real-time dynamic network;

[0046] The low-rank sparse model training module is used to constrain the local feature structure of each static network while removing the noise of each static network;

[0047] The building block of the non-negative matrix factorization training model, which is used to capture the inherent laws of the network and describe the potential characteristics of the network;

[0048] The optimization module is used to reduce the randomness of the netw...

Embodiment 2

[0065] This embodiment proposes a network structure deanonymization method based on matrix decomposition, such as figure 1 , including the following steps:

[0066] S1. Acquire the data source, the data source includes the topology structure of the relationship between various networks and the topology structure of the relationship between users in the network; that is, figure 2 The dynamic network shown, for example, the friendship topology on Tencent Weibo may be similar to the friendship topology on Facebook. These two networks have some common users, that is, the topology of the relationship between the networks, and the relationship between users in the network. The topology of the relationship is the topology of the relationship between users in a network;

[0067] S2, such as figure 2 , divide the data set of the dynamic social network into T static network data sets according to time, and obtain the adjacency matrix corresponding to each static network structure in...

Embodiment 3

[0085] As an optional implementation, the solution process of the target matrix includes:

[0086]

[0087] Among them, rank(S t ) means; λ means the damping coefficient; E t Represents the noise error matrix of the t-th static network; A t Represents the adjacency matrix of the t-th static network; S t Represents the target matrix of the tth static network; ||E t || 0 Represents the sparse noise constraint; S represents the target matrix after low-rank sparse model training; E represents the noise error matrix of the network.

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 relates to the field of network structure deanonymization, in particular to a network structure deanonymization system and method based on matrix decomposition, and the method comprisesthe steps: taking a data source which comprises a topological structure of a relation between networks and a topological structure of a relation between users in the networks; dividing the data set ofthe dynamic social network into T static network data sets according to the time, and obtaining an adjacent matrix corresponding to each piece of static network structure information; inputting the adjacent matrix, performing training according to a low-rank representation model, and calculating and obtaining a target matrix; inputting the target matrix into an improved non-negative matrix decomposition model for training and prediction to obtain a de-anonymized matrix of the target matrix. According to the method, low-rank training is carried out on network data, a prediction model of non-negative matrix factorization is combined, structure information and time sequence evolution of the network are considered in a combined mode, and the prediction accuracy is improved.

Description

technical field [0001] The invention relates to the field of network structure deanonymization, in particular to a matrix decomposition-based network structure deanonymization system and method. Background technique [0002] Social networks are now widely utilized by third-party consumers such as researchers and advertisers to understand user characteristics and behaviors. Usually, private or sensitive information contained in a collected dataset is anonymized before publishing the network data to prevent the compromise of personal privacy. In order to quantify the assurance level of privacy protection mechanisms and alleviate users' concerns, it becomes particularly important to study network deanonymization methods based on inferences from sensitive information. [0003] In social networks, due to the coexistence of private data and public data, there are three important privacy risks when social network data is released: content leakage risk, identity leakage risk and li...

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): H04L12/58H04L12/24G06F17/16
CPCH04L41/147H04L41/145H04L41/142G06F17/16H04L51/52
Inventor 陈幸吴涛先兴平明冠男
Owner CHONGQING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products