CN109829337A - A kind of method, system and the equipment of community network secret protection - Google Patents
A kind of method, system and the equipment of community network secret protection Download PDFInfo
- Publication number
- CN109829337A CN109829337A CN201910172130.6A CN201910172130A CN109829337A CN 109829337 A CN109829337 A CN 109829337A CN 201910172130 A CN201910172130 A CN 201910172130A CN 109829337 A CN109829337 A CN 109829337A
- Authority
- CN
- China
- Prior art keywords
- node
- community
- degree
- subgraph
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
This application discloses a kind of methods of community network secret protection, comprising: receives the original social network diagram of input；Community's division is carried out to node each in original social network diagram using default label propagation algorithm, obtains each community's subgraph；Each community's subgraph is reconstructed using subgraph restructing algorithm, the K degree anonymization of each community's subgraph is completed, to realize the secret protection of original social network diagram.Technical solution provided herein enhances the stability of algorithm; improve the effect of community's division; reduce influence of the label selection randomness to label propagation efficiency and result; and under the premise of protecting social networks network to stablize; minimally modification graph structure realizes that k degree is anonymous; enabling the social network data of publication, there is preferable availability the application to additionally provide system, equipment and the computer readable storage medium of a kind of community network secret protection simultaneously, have above-mentioned beneficial effect.
Description
Technical field
This application involves secret protection field, in particular to a kind of method of community network secret protection, system, equipment and
Computer readable storage medium.
Background technique
Social networks belongs to the research category of complex network, it is of interest that interaction and connection between social individual and individual,
It is modeled as diagram data usually to realize secret protection.Attacker often using the background knowledge about target individual possessed (such as
Connection relationship, neighborhood and insertion subgraph between the degree of node, identity property, node etc.) infer individual privacy information.Social network
The important privacy information of 2 classes (nodal community data and connection relationship data) that network is included is easily by node degree attack, link
The structurings such as attack attack.
And the secret protection for being directed to relation data is then the research hotspot of urgently people's further investigation, is usually modeled as figure
Data simultaneously upset such as random increase of method or figure modification method, deletion of node or side, and modification side right weight values using numerical value to realize
Secret protection.On the whole, how existing community network method for secret protection realizes various anonymization models such as if being mostly based on
Node k- is anonymous, subgraph k- is anonymous, k degree anonymity etc..
Realize that the main path of anonymization model has the method based on cluster and the method based on figure modification.However, being based on
The anonymity model of cluster causes network structure that great variety, data occur due to there is serious information loss after extensive
Effectiveness drastically reduces.And for diagram data modify or convert de-identification method all use mostly addition, deletion of node or side with
And the perturbation schemes such as Subgraph Isomorphism realize that k- degree is anonymous, but this figure modifies strategy at random and has ignored social networks immanent structure spy
Property, it can not still overcome the problems, such as biggish information loss.
Therefore, the information loss how reduced during community network secret protection is that those skilled in the art need at present
The technical issues of solution.
Summary of the invention
The purpose of the application is to provide the method for community network secret protection a kind of, system, equipment and computer-readable deposits
Storage media, for reducing the information loss during community network secret protection.
In order to solve the above technical problems, the application provides a kind of method of community network secret protection, this method comprises:
Receive the original social network diagram of input；
Community's division is carried out to node each in the original social network diagram using default label propagation algorithm, obtains each society
Area's subgraph；
Each community's subgraph is reconstructed using subgraph restructing algorithm, the K degree for completing each community's subgraph is anonymous
Change, to realize the secret protection of the original social network diagram.
Optionally, described that community stroke is carried out to node each in the original social network diagram using default label propagation algorithm
Point, obtain each community's subgraph, comprising:
Unique tags value is distributed respectively for each node in the original social network diagram；
The weighted value of each node is calculated, and each node is arranged by weighted value descending order, is obtained just
Beginning sequence；
Successively the unique tags value of each node is updated for the first time according to the initiation sequence；Wherein, described first
The secondary unique tags value for being updated to for the unique tags value of present node to be updated to the maximum neighbor node of weighted value；
Label iteration successively is carried out to the unique tags value of first updated each node according to the initiation sequence
It updates, until the unique tags value of each node no longer changes；Wherein, the label iteration is updated to present node only
One label value is updated to occur the most unique tags value of number in the unique tags value of each neighbor node；
The unique tags are worth identical node division to same community, obtain each community's subgraph.
Optionally, the weighted value for calculating each node, comprising:
According to formulaCalculate each weight index of the node based on degree；
According to formulaCalculate the node betweenness of each node；
According to formula I=eI0+I1+I2Calculate the weighted value of each node；
Wherein, I1For each weight index of the node based on degree, kiFor the degree of node i, N is the original social networks
The sum of figure interior joint, I2For the node betweenness of each node, σstFor the sum from node s to the shortest path of node t, σst
It (i) is the number of the shortest path from node s to node t and Jing Guo node i, I is the weighted value of each node, I0For each institute
State the basic weighted value of node.
Optionally, described that each community's subgraph is reconstructed using subgraph restructing algorithm, complete each community's
The K degree anonymization of figure, comprising:
According to formulaCalculate existing community
The node of each node of subgraph knows probability again；
It determinesWhen shifting number of edges mesh m；
To m side of the existing community subgraph random erasure, and increase m side at random, to realize to the existing community
The k degree of subgraph is anonymous；
Wherein, conf ({ ki} → i) it is that the node of each node of existing community subgraph knows probability again, Z is by mobile m
The number of edges of side posterior nodal point i, D is that the degree of the node i is kiEvent, P (Z=ki| D) it is the institute behind mobile m side
It states node i degree and remains as kiProbability；X is the degree of node u, and C is the event that the degree of the node u is du, P (X=ki|
C) for the degree of other nodes becomes k in addition to the node i behind mobile m sideiProbability, k is anonymous degree.
The application also provides a kind of system of community network secret protection, which includes:
Receiving module, original social network diagram for receiving input；
Community's division module, for being carried out using default label propagation algorithm to node each in the original social network diagram
Community divides, and obtains each community's subgraph；
K degree Anonymizing module completes each society for each community's subgraph to be reconstructed using subgraph restructing algorithm
The K degree anonymization of area's subgraph, to realize the secret protection of the original social network diagram.
Optionally, community's division module includes:
Label distribution sub module, for distributing unique tags respectively for each node in the original social network diagram
Value；
Weighted value computational submodule is dropped for calculating the weighted value of each node, and by each node by weighted value
Sequence sequence is arranged, and initiation sequence is obtained；
It is first to update submodule, for successively being carried out just to the unique tags value of each node according to the initiation sequence
Secondary update；Wherein, described to be updated to the unique tags value of present node being updated to the maximum neighbor node of weighted value for the first time
Unique tags value；
Label iteration updates submodule, for according to the initiation sequence successively to first updated each node
Unique tags value carries out the update of label iteration, until the unique tags value of each node no longer changes；Wherein, the label changes
In generation, is updated to occur number in the unique tags value that the unique tags value of present node is updated to each neighbor node at most only
One label value；
Submodule is divided, for the unique tags to be worth identical node division to same community, obtains each society
Area's subgraph.
Optionally, the weighted value computational submodule includes:
First computing unit, for according to formulaCalculate each weight index of the node based on degree；
Second computing unit, for according to formulaCalculate each node
Node betweenness；
Third computing unit, for according to formula I=eI0+I1+I2Calculate the weighted value of each node；
Wherein, I1For each weight index of the node based on degree, kiFor the degree of node i, N is the original social networks
The sum of figure interior joint, I2For the node betweenness of each node, σstFor the sum from node s to the shortest path of node t, σst
It (i) is the number of the shortest path from node s to node t and Jing Guo node i, I is the weighted value of each node, I0For each institute
State the basic weighted value of node.
Optionally, the K degree Anonymizing module includes:
Probability calculation submodule, for according to formula
Existing community subgraph is calculated respectively to save
The node of point knows probability again；
Submodule is determined, for determiningWhen shifting number of edges mesh m；
K degree anonymity submodule is used for m side of the existing community subgraph random erasure, and increases m side at random, with
It realizes anonymous to the k degree of the existing community subgraph；
Wherein, conf ({ ki}-→ i) it is that the node of each node of existing community subgraph knows probability again, Z is by moving
The number of edges of dynamic m side posterior nodal point i, D is that the degree of the node i is kiEvent, P (Z=ki| D) be behind mobile m side,
The node i degree remains as kiProbability；X is the degree of node u, and C is the event that the degree of the node u is du, P (X=
ki| C) it is that the degree of other nodes becomes k in addition to the node i behind mobile m sideiProbability, k is anonymous degree.
The application also provides a kind of community network secret protection equipment, which includes:
Memory, for storing computer program；
Processor, realizing the community network secret protection as described in any of the above-described when for executing the computer program
The step of method.
The application also provides a kind of computer readable storage medium, and calculating is stored on the computer readable storage medium
Machine program realizes the method for the community network secret protection as described in any of the above-described when the computer program is executed by processor
The step of.
The method of community network secret protection provided herein, comprising: receive the original social network diagram of input；It utilizes
Default label propagation algorithm carries out community's division to node each in original social network diagram, obtains each community's subgraph；Utilize subgraph
Each community's subgraph is reconstructed in restructing algorithm, the K degree anonymization of each community's subgraph is completed, to realize original social network diagram
Secret protection.
Technical solution provided herein, by utilizing default label propagation algorithm to the original social networks received
Each node carries out community's division in figure, obtains each community's subgraph, so that node updates sequence is controlled, and then enhances algorithm
Stability, improve the effect of community's division, reduce influence of the label selection randomness to label propagation efficiency and result；
By the way that each community's subgraph is reconstructed using subgraph restructing algorithm, the K degree anonymization of each community's subgraph is completed, so that protecting
Under the premise of social networks network is stablized, minimally modifies graph structure and realize that k degree is anonymous, enable the social networks of publication
Data have preferable availability.The application additionally provides system, equipment and the calculating of a kind of community network secret protection simultaneously
Machine readable storage medium storing program for executing has above-mentioned beneficial effect, and details are not described herein.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of application for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of flow chart of the method for community network secret protection provided by the embodiment of the present application；
Fig. 2 is a kind of practical manifestation mode of S102 in a kind of method of community network secret protection provided by Fig. 1
Flow chart；
Fig. 3 is a kind of flow chart of practical manifestation mode of step S202 in Fig. 2；
Fig. 4 is a kind of practical manifestation mode of S103 in a kind of method of community network secret protection provided by Fig. 1
Flow chart；
Fig. 5 is a kind of structure chart of the system of community network secret protection provided by the embodiment of the present application；
Fig. 6 is the structure chart of the system of another kind community network secret protection provided by the embodiment of the present application；
Fig. 7 is a kind of structure chart of community network secret protection equipment provided by the embodiment of the present application.
Specific embodiment
The core of the application is to provide the method for community network secret protection a kind of, system, equipment and computer-readable deposits
Storage media, for reducing the information loss during community network secret protection.
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
Referring to FIG. 1, Fig. 1 is a kind of process of the method for community network secret protection provided by the embodiment of the present application
Figure.
It specifically comprises the following steps:
S101: the original social network diagram of input is received；
Based on the anonymity model of cluster due to there is serious information loss after extensive, network structure is caused to occur huge
Big variation, data effectiveness drastically reduce.And the de-identification method modified or converted for diagram data all uses addition mostly, deletes
It is anonymous that the perturbation schemes such as node or side and Subgraph Isomorphism realize k- degree, but this figure modifies strategy at random and has ignored social networks
Immanent structure characteristic can not still overcome the problems, such as biggish information loss；The application proposes a kind of side of community network secret protection
Method minimally modifies graph structure under the premise of protecting the stabilization of social networks network, realizes that k degree is anonymous, so that
The social network data of publication has preferable availability；
The application is described complicated between the userspersonal information for including in social network data and user using graph structure model G
Social networks, figure interior joint V represents the individual in social networks, and side E represents the association between individual.It is hidden that community is divided into introducing
Private protection will affect the identical node division of power as one kind, and carry out the secret protection of strength degree to it.
S102: community's division is carried out to node each in original social network diagram using default label propagation algorithm, is obtained each
Community's subgraph；
Optionally, default label propagation algorithm mentioned herein, is specifically as follows the mark of aggregators influence power factor
Propagation algorithm is signed, is described in detail below with reference to Fig. 2:
Referring to FIG. 2, a kind of reality of the Fig. 2 for S102 in a kind of method of community network secret protection provided by Fig. 1
The flow chart of manifestation mode.
Itself specifically includes the following steps:
S201: unique tags value is distributed respectively for each node in original social network diagram；
S202: the weighted value of each node is calculated, and each node is arranged by weighted value descending order, obtains initial sequence
Column；
S203: successively the unique tags value of each node is updated for the first time according to initiation sequence；
First update mentioned herein is that the unique tags value of present node is updated to the maximum neighbours of weighted value to save
The unique tags value of point, that is, first determine the maximum neighbor node of weighted value of present node, then only by present node
One label value is updated to the unique tags value of the neighbor node, its object is to enable the label value of the node of high weight consistent, i.e.,
The identical node division of power be will affect as one kind.
S204: label iteration successively is carried out more to the unique tags value of first updated each node according to initiation sequence
Newly, until the unique tags value of each node no longer changes；
It is that the unique tags value of present node is updated to each neighbor node only that label iteration mentioned herein, which updates,
Occur the most unique tags value of number in one label value, its object is to enable the label value of the node of high weight consistent, so that
The big node of influence power is easier to be transmitted, and the accuracy of community's division is promoted with this；
Further, identical and be all maximum value if there is multiple labels number occur in neighbor node, it chooses and wherein weighs
Unique tags value of the unique tags value label of the maximum neighbor node of weight values as present node.
S205: unique tags are worth identical node division to same community, obtain each community's subgraph.
Community's division is carried out by using the label propagation algorithm of aggregators influence power factor, it being capable of comprehensive assessment node
Influence power and calculate the weighted value of each node, and the sequence asynchronous refresh label according to node influence power from high to low makes
After obtaining the update of label iteration, local core node will possess higher weights value, and the identical node of label can be divided
Enter a community, and then enhance algorithm stability, promote the effect that community divides, reduces label selection randomness and label is propagated
The influence of efficiency and result.
S103: being reconstructed each community's subgraph using subgraph restructing algorithm, complete the K degree anonymization of each community's subgraph,
To realize the secret protection of original social network diagram.
After community divides, the application is reconstructed community's subgraph using subgraph restructing algorithm, completes each community's
The K degree anonymization of figure, and then realize the secret protection of original social network diagram.
Based on the above-mentioned technical proposal, the method for a kind of community network secret protection provided herein, by using in advance
Bidding label propagation algorithm carries out community's division to node each in the original social network diagram received, obtains each community's subgraph, makes
It obtains node updates sequence to be controlled, and then enhances the stability of algorithm, improve the effect of community's division, reduce label
Select influence of the randomness to label propagation efficiency and result；By carrying out weight to each community's subgraph using subgraph restructing algorithm
Structure completes the K degree anonymization of each community's subgraph, so that under the premise of protecting social networks network to stablize, minimum
Ground modifies graph structure and realizes that k degree is anonymous, and the social network data of publication is enabled to have preferable availability.
It is directed to the step S202 of an embodiment, it, specifically can be with wherein the described weighted value for calculating each node
For step as shown in Figure 3, it is illustrated below with reference to Fig. 3.
Referring to FIG. 3, Fig. 3 is a kind of flow chart of practical manifestation mode of step S202 in Fig. 2.
Itself specifically includes the following steps:
S301: according to formulaCalculate weight index of each node based on degree；
Degree can describe the link distribution situation between social networks interior joint, for a non-directed graph G=[V, E], node
The degree ki of Vi is equal to the sum of other all interstitial contents being connected with the node, is the important finger of a network node self-characteristic
Mark.In general, the influence power of node and the degree of node are positively correlated.
S302: according to formulaCalculate the node betweenness of each node；
Node betweenness indicates to account for all shortest path sums by the shortest path between all nodes of the node in network
Ratio, betweenness is able to reflect the status of different members in network, is the important indicator of a description network node global property.
Generally, node influence power and node betweenness are positively correlated.Node betweenness is bigger, and member exchanges the dependence to the node in social networks
Property is stronger.
S303: according to formula I=eI0+I1+I2Calculate the weighted value of each node；
Comprehensively consider the self-characteristic and global property calculate node weight of node, node weights and its own influence power and
The influence power of other nodes is positively correlated, therefore the label weight I of node can be expressed as I=eI0+I1+I2；
Wherein, I1Weight index for each node based on degree, kiFor the degree of node i, N is original social network diagram interior joint
Sum, I2For the node betweenness of each node, σstFor the sum from node s to the shortest path of node t, σstIt (i) is from node s
The number of shortest path to node t and Jing Guo node i, I are the weighted value of each node, I0For the basic weighted value of each node.
Be directed to the step S103 of an embodiment, wherein it is described using subgraph restructing algorithm to each community's subgraph into
Row reconstruct, the K degree anonymization for completing each community's subgraph are specifically as follows with realizing the secret protection of original social network diagram
Step as shown in Figure 4, is illustrated below with reference to Fig. 4.
Referring to FIG. 4, a kind of reality of the Fig. 4 for S103 in a kind of method of community network secret protection provided by Fig. 1
The flow chart of manifestation mode.
Itself specifically includes the following steps:
S401: according to formulaIt calculates current
The node of each node of community's subgraph knows probability again；
Assuming that the degree ki of the known publication figure G and victim Node i of attacker, behind mobile m side, he can identify again
The probability of egress is are as follows:
S403: to existing community m side of subgraph random erasure, and increasing m side at random, to realize to existing community subgraph
K degree it is anonymous；
Wherein, conf ({ ki} → i) it is that the node of each node of existing community subgraph knows probability again, Z is by mobile m side
The number of edges of posterior nodal point i, D are that the degree of node i is kiEvent, P (Z=ki| D) it is behind mobile m side, node i degree is still
It is so kiProbability；X is the degree of node u, the event that the degree that C is node u is du, P (X=ki| C) it is by mobile m side
The degree of other nodes becomes k in addition to node i afterwardsiProbability, k is anonymous degree；
The node that present application embodiment first calculates each node of existing community subgraph knows probability again, then selects the condition of satisfaction
Shifting number of edges mesh m then increase m side at random finally by mobile m side, i.e. m side of first random erasure, realize to community
The k degree of subgraph is anonymous.
Referring to FIG. 5, Fig. 5 is a kind of structure of the system of community network secret protection provided by present application embodiment
Figure.
The system may include:
Receiving module 100, original social network diagram for receiving input；
Community's division module 200, for being carried out using default label propagation algorithm to node each in original social network diagram
Community divides, and obtains each community's subgraph；
K degree Anonymizing module 300 completes each community's for each community's subgraph to be reconstructed using subgraph restructing algorithm
The K degree anonymization of figure, to realize the secret protection of original social network diagram.
Referring to FIG. 6, Fig. 6 is the structure of the system of another kind community network secret protection provided by the embodiment of the present application
Figure.
Community's division module 200 may include:
Label distribution sub module, for distributing unique tags value respectively for each node in original social network diagram；
Weighted value computational submodule, for calculating the weighted value of each node, and by each node by weighted value descending order into
Row arrangement, obtains initiation sequence；
It is first to update submodule, for successively being updated for the first time to the unique tags value of each node according to initiation sequence；
Wherein, it is updated to for the unique tags value of present node to be updated to the unique tags value of the maximum neighbor node of weighted value for the first time；
Label iteration updates submodule, for according to initiation sequence successively to the unique tags of first updated each node
Value carries out the update of label iteration, until the unique tags value of each node no longer changes；Wherein, label iteration is updated to that prosthomere will be worked as
The unique tags value of point is updated to occur the most unique tags value of number in the unique tags value of each neighbor node；
It divides submodule and obtains each community's subgraph for unique tags to be worth identical node division to same community.
Further, which may include:
First computing unit, for according to formulaCalculate weight index of each node based on degree；
Second computing unit, for according to formulaCalculate the node of each node
Betweenness；
Third computing unit, for according to formula I=eI0+I1+I2Calculate the weighted value of each node；
Wherein, I1Weight index for each node based on degree, kiFor the degree of node i, N is original social network diagram interior joint
Sum, I2For the node betweenness of each node, σstFor the sum from node s to the shortest path of node t, σstIt (i) is from node s
The number of shortest path to node t and Jing Guo node i, I are the weighted value of each node, I0For the basic weighted value of each node.
The K degree Anonymizing module 300 may include:
Probability calculation submodule, for according to formula
Existing community subgraph is calculated respectively to save
The node of point knows probability again；
Submodule is determined, for determiningWhen shifting number of edges mesh m；
K degree anonymity submodule is used for existing community m side of subgraph random erasure, and increases m side at random, to realize
It is anonymous to the k degree of existing community subgraph；
Wherein, conf ({ ki}-→ i) it is that the node of each node of existing community subgraph knows probability again, Z is by mobile m item
The number of edges of side posterior nodal point i, D are that the degree of node i is kiEvent, P (Z=ki| D) it is the node i degree behind mobile m side
Remain as kiProbability；X is the degree of node u, the event that the degree that C is node u is du, P (X=ki| C) it is by mobile m item
The degree of other nodes becomes k in addition to node i behind sideiProbability, k is anonymous degree.
Since the embodiment of components of system as directed is corresponded to each other with the embodiment of method part, the embodiment of components of system as directed is asked
Referring to the description of the embodiment of method part, wouldn't repeat here.
Referring to FIG. 7, Fig. 7 is a kind of structure chart of community network secret protection equipment provided by the embodiment of the present application.
The community network secret protection equipment 700 can generate bigger difference because configuration or performance are different, can wrap
One or more processors (central processing units, CPU) 722 is included (for example, at one or more
Manage device) and memory 732, one or more store storage medium 730 (such as one of application programs 742 or data 744
Or more than one mass memory unit).Wherein, memory 732 and storage medium 730 can be of short duration storage or persistent storage.
The program for being stored in storage medium 730 may include one or more modules (diagram does not mark), and each module can wrap
It includes to the series of instructions operation in device.Further, central processing unit 722 can be set to logical with storage medium 730
Letter executes the series of instructions operation in storage medium 730 in community network secret protection equipment 700.
Community network secret protection equipment 700 can also include one or more power supplys 727, one or more
Wired or wireless network interface 750, one or more input/output interfaces 758, and/or, one or more operations
System 741, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..
Step in the method for community network secret protection described in above-mentioned Fig. 1 to Fig. 4 is by community network secret protection
Equipment is based on the structure shown in Fig. 7 and realizes.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed device, device and method, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the division of module,
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple module or components can be with
In conjunction with or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING of device or module or
Communication connection can be electrical property, mechanical or other forms.
Module may or may not be physically separated as illustrated by the separation member, show as module
Component may or may not be physical module, it can and it is in one place, or may be distributed over multiple networks
In module.Some or all of the modules therein can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, can integrate in a processing module in each functional module in each embodiment of the application
It is that modules physically exist alone, can also be integrated in two or more modules in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.
If integrated module is realized and when sold or used as an independent product in the form of software function module, can
To be stored in a computer readable storage medium.Based on this understanding, the technical solution of the application substantially or
Say that all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Out, which is stored in a storage medium, including some instructions are used so that a computer equipment
The whole of (can be personal computer, funcall device or the network equipment etc.) execution each embodiment method of the application
Or part steps.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (Read-Only Memory,
ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. are various can store program
The medium of code.
Above to a kind of method of community network secret protection provided herein, system, equipment and computer-readable
Storage medium is described in detail.Specific case used herein explains the principle and embodiment of the application
It states, the description of the example is only used to help understand the method for the present application and its core ideas.It should be pointed out that for this skill
For the those of ordinary skill in art field, under the premise of not departing from the application principle, several change can also be carried out to the application
Into and modification, these improvement and modification also fall into the protection scope of the claim of this application.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence " including one ... ", not
There is also other identical elements in the process, method, article or equipment for including element for exclusion.
Claims (10)
1. a kind of method of community network secret protection characterized by comprising
Receive the original social network diagram of input；
Community's division is carried out to node each in the original social network diagram using default label propagation algorithm, obtains each community's
Figure；
Each community's subgraph is reconstructed using subgraph restructing algorithm, completes the K degree anonymization of each community's subgraph, with
Realize the secret protection of the original social network diagram.
2. the method according to claim 1, wherein described utilize default label propagation algorithm to the original society
It hands over each node in network to carry out community's division, obtains each community's subgraph, comprising:
Unique tags value is distributed respectively for each node in the original social network diagram；
The weighted value of each node is calculated, and each node is arranged by weighted value descending order, obtains initial sequence
Column；
Successively the unique tags value of each node is updated for the first time according to the initiation sequence；Wherein, it is described it is first more
The new unique tags value for the unique tags value of present node to be updated to the maximum neighbor node of weighted value；
The update of label iteration successively is carried out to the unique tags value of first updated each node according to the initiation sequence,
Until the unique tags value of each node no longer changes；Wherein, the label iteration is updated to unique mark of present node
Label value is updated to occur the most unique tags value of number in the unique tags value of each neighbor node；
The unique tags are worth identical node division to same community, obtain each community's subgraph.
3. according to the method described in claim 2, it is characterized in that, the weighted value for calculating each node, comprising:
According to formulaCalculate each weight index of the node based on degree；
According to formulaCalculate the node betweenness of each node；
According to formulaCalculate the weighted value of each node；
Wherein, I1For each weight index of the node based on degree, kiFor the degree of node i, N is in the original social network diagram
The sum of node, I2For the node betweenness of each node, σstFor the sum from node s to the shortest path of node t, σst(i)
For the number of the shortest path from node s to node t and Jing Guo node i, I is the weighted value of each node, I0It is each described
The basic weighted value of node.
4. the method according to claim 1, wherein described utilize subgraph restructing algorithm to each community's subgraph
It is reconstructed, completes the K degree anonymization of each community's subgraph, comprising:
According to formulaCalculate existing community subgraph
The node of each node knows probability again；
It determinesWhen shifting number of edges mesh m；
To m side of the existing community subgraph random erasure, and increase m side at random, to realize to the existing community subgraph
K degree it is anonymous；
Wherein, conf ({ ki} → i) it is that the node of each node of existing community subgraph knows probability again, Z is by mobile m side
The number of edges of posterior nodal point i, D are that the degree of the node i is kiEvent, P (Z=ki| D) it is the section behind mobile m side
Point i degree remains as kiProbability；X is the degree of node u, and C is the event that the degree of the node u is du, P (X=ki| C) be
The degree of other nodes becomes k in addition to the node i behind mobile m sideiProbability, k is anonymous degree.
5. a kind of system of community network secret protection characterized by comprising
Receiving module, original social network diagram for receiving input；
Community's division module, for carrying out community to node each in the original social network diagram using default label propagation algorithm
It divides, obtains each community's subgraph；
K degree Anonymizing module completes each community's for each community's subgraph to be reconstructed using subgraph restructing algorithm
The K degree anonymization of figure, to realize the secret protection of the original social network diagram.
6. system according to claim 5, which is characterized in that community's division module includes:
Label distribution sub module, for distributing unique tags value respectively for each node in the original social network diagram；
Weighted value computational submodule, for calculating the weighted value of each node, and each node is suitable by weighted value descending
Sequence is arranged, and initiation sequence is obtained；
It is first to update submodule, for successively being carried out for the first time more to the unique tags value of each node according to the initiation sequence
Newly；Wherein, described to be updated to the unique tags value of present node being updated to the unique of the maximum neighbor node of weighted value for the first time
Label value；
Label iteration updates submodule, for according to the initiation sequence successively to the unique of first updated each node
Label value carries out the update of label iteration, until the unique tags value of each node no longer changes；Wherein, the label iteration is more
New is that the unique tags value of present node is updated to occur the most unique mark of number in the unique tags value of each neighbor node
Label value；
Submodule is divided, for the unique tags to be worth identical node division to same community, obtains each community's
Figure.
7. system according to claim 6, which is characterized in that the weighted value computational submodule includes:
First computing unit, for according to formulaCalculate each weight index of the node based on degree；
Second computing unit, for according to formulaCalculate the node of each node
Betweenness；
Third computing unit, for according to formulaCalculate the weighted value of each node；
Wherein, I1For each weight index of the node based on degree, kiFor the degree of node i, N is in the original social network diagram
The sum of node, I2For the node betweenness of each node, σstFor the sum from node s to the shortest path of node t, σst(i)
For the number of the shortest path from node s to node t and Jing Guo node i, I is the weighted value of each node, I0It is each described
The basic weighted value of node.
8. system according to claim 5, which is characterized in that the K degree Anonymizing module includes:
Probability calculation submodule, for according to formula
Calculate each node of existing community subgraph
Node knows probability again；
Submodule is determined, for determiningWhen shifting number of edges mesh m；
K degree anonymity submodule is used for m side of the existing community subgraph random erasure, and increases m side at random, to realize
It is anonymous to the k degree of the existing community subgraph；
Wherein, conf ({ ki} → i) it is that the node of each node of existing community subgraph knows probability again, Z is by mobile m side
The number of edges of posterior nodal point i, D are that the degree of the node i is kiEvent, P (Z=ki| D) it is the section behind mobile m side
Point i degree remains as kiProbability；X is the degree of node u, and C is the event that the degree of the node u is du, P (X=ki| D) be
The degree of other nodes becomes k in addition to the node i behind mobile m sideiProbability, k is anonymous degree.
9. a kind of community network secret protection equipment characterized by comprising
Memory, for storing computer program；
Processor realizes that community network privacy is protected as described in any one of Claims 1-4 when for executing the computer program
The step of method of shield.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the community network secret protection as described in any one of Claims 1-4 when the computer program is executed by processor
Method the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910172130.6A CN109829337B (en) | 2019-03-07 | 2019-03-07 | Method, system and equipment for protecting social network privacy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910172130.6A CN109829337B (en) | 2019-03-07 | 2019-03-07 | Method, system and equipment for protecting social network privacy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109829337A true CN109829337A (en) | 2019-05-31 |
| CN109829337B CN109829337B (en) | 2023-07-25 |
Family
ID=66865637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910172130.6A Active CN109829337B (en) | 2019-03-07 | 2019-03-07 | Method, system and equipment for protecting social network privacy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109829337B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210248A (en) * | 2019-06-13 | 2019-09-06 | 重庆邮电大学 | A kind of network structure towards secret protection goes anonymization systems and method |
| CN110443069A (en) * | 2019-08-06 | 2019-11-12 | 广东工业大学 | A kind of method, system and the equipment of mobile social networking secret protection |
| CN111046429A (en) * | 2019-12-13 | 2020-04-21 | 支付宝(杭州)信息技术有限公司 | Method and device for establishing relationship network based on privacy protection |
| CN111159577A (en) * | 2019-12-31 | 2020-05-15 | 北京明略软件***有限公司 | Community division method and device, storage medium and electronic device |
| CN111178678A (en) * | 2019-12-06 | 2020-05-19 | 中国人民解放军战略支援部队信息工程大学 | Network node importance evaluation method based on community influence |
| CN111401196A (en) * | 2020-03-10 | 2020-07-10 | 珠海全志科技股份有限公司 | Method, computer device and computer readable storage medium for self-adaptive face clustering in limited space |
| CN111597664A (en) * | 2020-04-03 | 2020-08-28 | 厦门道唯思信息技术有限公司 | Social network layout method, system and storage medium thereof |
| CN113127699A (en) * | 2021-04-28 | 2021-07-16 | 三峡大学 | Personalized anonymous social network privacy protection method |
| CN114662143A (en) * | 2022-02-28 | 2022-06-24 | 北京交通大学 | Sensitive link privacy protection method based on graph embedding |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090303237A1 (en) * | 2008-06-06 | 2009-12-10 | International Business Machines Corporation | Algorithms for identity anonymization on graphs |
| CN106980795A (en) * | 2017-02-28 | 2017-07-25 | 广西师范大学 | Community network data-privacy guard method |
-
2019
- 2019-03-07 CN CN201910172130.6A patent/CN109829337B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090303237A1 (en) * | 2008-06-06 | 2009-12-10 | International Business Machines Corporation | Algorithms for identity anonymization on graphs |
| CN106980795A (en) * | 2017-02-28 | 2017-07-25 | 广西师范大学 | Community network data-privacy guard method |
Non-Patent Citations (5)
| Title |
|---|
| 季青松等: "有效改善标签传播算法鲁棒性的途径", 《信息安全与通信保密》 * |
| 宋喜忠等: "基于k-subgrap算法的社交网络隐私保护研究", 《科技通报》 * |
| 郑少强等: "一种面向社区发现的高鲁棒性标签传播算法", 《小型微型计算机***》 * |
| 陆越等: "融合社团划分的社交网络分级隐私保护算法", 《通信技术》 * |
| 龚卫华等: "基于k-度匿名的社会网络隐私保护方法", 《电子学报》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210248A (en) * | 2019-06-13 | 2019-09-06 | 重庆邮电大学 | A kind of network structure towards secret protection goes anonymization systems and method |
| CN110443069A (en) * | 2019-08-06 | 2019-11-12 | 广东工业大学 | A kind of method, system and the equipment of mobile social networking secret protection |
| CN110443069B (en) * | 2019-08-06 | 2023-07-25 | 广东工业大学 | Method, system and equipment for protecting privacy of mobile social network |
| CN111178678B (en) * | 2019-12-06 | 2022-11-08 | 中国人民解放军战略支援部队信息工程大学 | Network node importance evaluation method based on community influence |
| CN111178678A (en) * | 2019-12-06 | 2020-05-19 | 中国人民解放军战略支援部队信息工程大学 | Network node importance evaluation method based on community influence |
| CN111046429A (en) * | 2019-12-13 | 2020-04-21 | 支付宝(杭州)信息技术有限公司 | Method and device for establishing relationship network based on privacy protection |
| CN111159577A (en) * | 2019-12-31 | 2020-05-15 | 北京明略软件***有限公司 | Community division method and device, storage medium and electronic device |
| CN111159577B (en) * | 2019-12-31 | 2024-02-27 | 北京明略软件***有限公司 | Community dividing method and device, storage medium and electronic device |
| CN111401196A (en) * | 2020-03-10 | 2020-07-10 | 珠海全志科技股份有限公司 | Method, computer device and computer readable storage medium for self-adaptive face clustering in limited space |
| CN111597664A (en) * | 2020-04-03 | 2020-08-28 | 厦门道唯思信息技术有限公司 | Social network layout method, system and storage medium thereof |
| CN111597664B (en) * | 2020-04-03 | 2021-12-31 | 厦门道唯思信息技术有限公司 | Social network layout method, system and storage medium thereof |
| CN113127699A (en) * | 2021-04-28 | 2021-07-16 | 三峡大学 | Personalized anonymous social network privacy protection method |
| CN114662143A (en) * | 2022-02-28 | 2022-06-24 | 北京交通大学 | Sensitive link privacy protection method based on graph embedding |
| CN114662143B (en) * | 2022-02-28 | 2024-05-03 | 北京交通大学 | Sensitive link privacy protection method based on graph embedding |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109829337B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829337A (en) | A kind of method, system and the equipment of community network secret protection | |
| Ozfatura et al. | Speeding up distributed gradient descent by utilizing non-persistent stragglers | |
| He et al. | TIFIM: A two-stage iterative framework for influence maximization in social networks | |
| Starnini et al. | Random walks on temporal networks | |
| Mata et al. | Heterogeneous pair-approximation for the contact process on complex networks | |
| Tekin et al. | Multi-objective contextual multi-armed bandit with a dominant objective | |
| CN109598563A (en) | Brush single detection method, device, storage medium and electronic equipment | |
| CN103325061B (en) | A kind of community discovery method and system | |
| CN107784598A (en) | A kind of network community discovery method | |
| CN106096075A (en) | A kind of message propagation model based on social networks | |
| CN106951524A (en) | Overlapping community discovery method based on node influence power | |
| CN103365727A (en) | Host load forecasting method in cloud computing environment | |
| Li et al. | Deep reinforcement learning: Algorithm, applications, and ultra-low-power implementation | |
| CN108809697A (en) | Social networks key node recognition methods based on maximizing influence and system | |
| Zhou et al. | Cost-aware partitioning for efficient large graph processing in geo-distributed datacenters | |
| CN108880846A (en) | The method and device of vector representation is determined for nodes | |
| CN109583227A (en) | A kind of method for protecting privacy, apparatus and system | |
| Tang et al. | An adaptive discrete particle swarm optimization for influence maximization based on network community structure | |
| Xu et al. | Power-law graphs have minimal scaling of Kemeny constant for random walks | |
| Cao et al. | Brief announcement: An improved distributed approximate single source shortest paths algorithm | |
| CN109802859A (en) | Nodes recommendations method and server in a kind of network | |
| CN111178678B (en) | Network node importance evaluation method based on community influence | |
| Eppstein et al. | Extended dynamic subgraph statistics using h-index parameterized data structures | |
| Yang et al. | Trust-based scheduling strategy for cloud workflow applications | |
| CN113992520B (en) | Virtual network resource deployment method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |