Track data privacy protection method and system based on Wien graph and differential privacy

Through the method based on Venn diagram and differential privacy, the concept of trajectory data intersection and obfuscating the center of the circle is used to protect the trajectory data, solving the problem of low security of trajectory privacy data in the existing technology, and effectively resisting malicious attacks and data security improvement.

CN118916915AActive Publication Date: 2024-11-08JIAMUSI UNIVERSITY
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411091645.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-08
Estimated Expiration
2044-08-09

AI Technical Summary

Technical Problem

Existing track privacy data protection methods are low in security when facing malicious attacks with background knowledge and cannot effectively prevent privacy leakage.

Method used

Using a method based on Venn diagram and differential privacy, the user's trajectory data is protected by intersecting the trajectory data with friend users, using the concept of meshing and confusing the center of the circle, replacing the coordinate points of the repeated position to achieve data protection.

Benefits of technology

Effectively resist malicious inference under background knowledge, improves the security of trajectory data, while ensuring data availability and improving the security of privacy protection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118916915A_ABST
    Figure CN118916915A_ABST
Patent Text Reader

Abstract

The invention discloses a trajectory data privacy protection method and system based on a Wien graph and differential privacy, and relates to the field of privacy protection. The method aims at solving the problem that an existing track privacy data safety protection method is low in safety. The method comprises the following steps: acquiring friend users of a to-be-protected track user A, and dispersing coordinates of places on the track of each friend user into a geographic space after grid division; acquiring a place coordinate set contained in the track of the ith friend user of the user A; and obtaining an intersection C of the site coordinate sets in the tracks of all friend users of the user A, and carrying out privacy protection on the site coordinates in the intersection C to obtain the track of the user A after privacy protection. The method and the device are used for performing privacy protection on the trajectory data of the user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of privacy protection, and in particular to a trajectory data privacy protection method and system based on Venn diagram and differential privacy. Background Art

[0002] With the widespread use of mobile devices and location services, users' trajectory data is being collected and used in large quantities, which improves service quality and user experience while also bringing serious privacy risks. Unprotected trajectory data may expose users' personal privacy information and may even be used maliciously.

[0003] At present, trajectory data privacy protection technology mainly focuses on two aspects: online application trajectory data privacy protection and offline application trajectory data privacy protection. Online application trajectory data privacy protection provides users with corresponding efficient services through the real-time location of mobile objects, such as intelligent traffic management, mobile medical services, etc.; offline application trajectory data privacy protection analyzes and mines the data collected by individuals or specific institutions, thereby collecting sensitive information of other individuals, such as home address, work location, lifestyle and health status, etc. However, under the premise of having background knowledge, the adversary will make malicious inferences about the privacy of individual trajectory data. Therefore, the existing methods cannot effectively curb the malicious attacks and privacy leakage risks through background knowledge, resulting in low security of the existing trajectory privacy data security protection methods. Summary of the invention

[0004] The purpose of the present invention is to solve the problem of low security of existing trajectory privacy data security protection methods, and propose a trajectory data privacy protection method and system based on Venn diagram and differential privacy.

[0005] A trajectory data privacy protection method based on Venn diagram and differential privacy includes the following steps:

[0006] Step 1: Obtain the friend users of user A whose trajectory is to be protected, and discretize the coordinates of the locations on each friend user's trajectory into the geographic space after grid division;

[0007] Step 2: Get the location coordinate set F contained in the trajectory of user A’s i-th friend i =(x i,1 ,x i,2 ,x i,n ,....,x i,N );

[0008] Among them, F i is the set of location coordinates contained in the trajectory of the i-th friend user, x i,n is the coordinates of n locations on the trajectory of the i-th friend user; N is the total number of locations on the trajectory of the i-th friend user;

[0009] Step 3: Obtain the intersection C of the location coordinate sets in the trajectories of all friend users of user A, and perform privacy protection on the location coordinates in the intersection C to obtain the trajectory of user A after privacy protection.

[0010] Furthermore, in step 3, the intersection C of the location coordinate sets in the trajectories of all the friend users of user A is obtained, and the location coordinates in the intersection C are privacy protected to obtain the trajectory of user A after privacy protection, specifically:

[0011] Step 31: Get the intersection C of the location coordinates of all friend user trajectories of user A:

[0012]

[0013] Among them, s is the total number of user A’s friends. is the coordinate of the i*th location in the intersection C, is the coordinate of the N*th location in the intersection C, N* is the total number of locations in the intersection C;

[0014] Step 32: Use intersection C to obtain the trajectory of user A after privacy protection.

[0015] Furthermore, the trajectory of user A after privacy protection is obtained by using the intersection C in step 32, specifically:

[0016] Step 321: Initialize user A's friend user number i=1;

[0017] Step 322: As the center of the circle, draw a circle with r as the radius to obtain the circular area And initialize The location number j in the inner part is 1;

[0018] Step 323: Get points The utility value

[0019] in, yes The j-th location coordinates within;

[0020] Step 324: Point-based The utility value Get The probability of being the center of the circle

[0021] Step 325: Determine whether j is equal to k. If j < k, set j = j + 1 and return to step 323; if j = k, set The location corresponding to the maximum value is The center of confusion;

[0022] Where k is Total number of locations within

[0023] Step 326: Determine whether i* is less than N*. If i*<N*, set i*=i*+1 and return to step 322; if i*=N*, output all the confusion circle centers, the privacy-protected trajectory of user A composed of all the confusion circle centers, and publish the privacy-protected trajectory of user A.

[0024] Furthermore, the acquisition point in step 323 The utility value Specifically:

[0025]

[0026] in, Yes To point The Euclidean distance of The total number of locations within.

[0027] Further, the point-based The utility value Get The probability of being the center of the circle Specifically:

[0028]

[0029] Where ΔU is the sensitivity, ε is the privacy budget parameter, yes As The probability of the center of the circle.

[0030] A trajectory data privacy protection system based on Venn diagram and differential privacy, comprising: a friend user trajectory location coordinate acquisition module, a friend user trajectory intersection acquisition module, a confusion circle center location acquisition module, and a privacy protected user trajectory generation module;

[0031] The friend user trajectory location coordinate acquisition module is used to obtain the location coordinates in the friend user trajectory of the to-be-protected trajectory user A, and discretize the location coordinates into the geographic space after grid division, and obtain the location coordinate set F contained in the i-th friend user trajectory of user A i =(x i,1 ,x i,2 ,x i,n ,....,x i,N );

[0032] Among them, F i is the set of location coordinates contained in the trajectory of the i-th friend user, xi,n is the coordinates of n locations on the trajectory of the i-th friend user; N is the total number of locations on the trajectory of the i-th friend user;

[0033] The friend user trajectory intersection acquisition module acquires the intersection C of the location coordinate sets in all friend user trajectories of user A;

[0034] The confusion center location acquisition module is used to draw a circle with each location in the intersection C as the center, and obtain the confusion center location of each circle;

[0035] The privacy-protected user trajectory generation module uses each confusion circle center location to compose the privacy-protected trajectory of user A and publishes it.

[0036] Furthermore, the friend user trajectory intersection acquisition module acquires the intersection C of the location coordinate sets in all friend user trajectories of user A, specifically:

[0037]

[0038] Among them, s is the total number of user A’s friends. is the coordinate of the i*th location in the intersection C, is the coordinate of the N*th location in the intersection C, and N* is the total number of locations in the intersection C.

[0039] Furthermore, the confusion center location acquisition module is used to draw a circle with each location in the intersection C as the center to obtain the confusion center location of each circle, specifically:

[0040] S1. Initialize the friend user number i of user A = 1;

[0041] S2. As the center of the circle, draw a circle with r as the radius to obtain the circular area And initialize The location number j in the inner part is 1;

[0042] S3, Get Point The utility value

[0043] in, yes The j-th location coordinates within;

[0044] S4, point-based The utility value Get The probability of being the center of the circle

[0045] S5. Determine whether j is equal to k. If j < k, set j = j + 1 and return to S3. If j = k, set The location corresponding to the maximum value is The center of confusion;

[0046] Where k is Total number of locations within

[0047] S6. Determine whether i* is less than N*. If i*<N*, set i*=i*+1 and return to step S2; if i*=N*, output all the confusion circle centers.

[0048] Furthermore, the acquisition point in S3 The utility value Specifically:

[0049]

[0050] in, Yes To point The Euclidean distance of The total number of locations within.

[0051] Furthermore, the point-based The utility value Get The probability of being the center of the circle Specifically:

[0052]

[0053] Where ΔU is the sensitivity, ε is the privacy budget parameter, yes As The probability of the center of the circle.

[0054] The beneficial effects of the present invention are:

[0055] The present invention uses grids to divide the real geographic space and converts the user trajectory data set into grid position coordinate points. In order to prevent attackers from using background knowledge to infer individual sensitive information, the present invention uses the method of the relationship between Venn diagram sets, inputs the position coordinate point set of the friend users of the user to be protected, and statistically outputs the repeated position coordinate point set of the friend users. Each position coordinate point in the repeated position coordinate point set is used as the center of a circle, and a position coordinate point in the circular area is selected to replace the center position coordinate point using the index mechanism of differential privacy, so as to achieve protection of the repeated position coordinate points, and then achieve protection of the privacy of individual trajectory data. The present invention can effectively resist the malicious inference of the privacy of individual trajectory data by the adversary under the premise of having background knowledge. While effectively protecting the privacy of trajectory data, the availability of trajectory data is guaranteed, and the security of the trajectory privacy data security protection method is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 Spatial partitioning results into geographic grids;

[0057] Figure 2 It is the set relationship of Venn diagram;

[0058] Figure 3 Schematic diagram of the privacy protection scheme. DETAILED DESCRIPTION

[0059] Specific implementation method 1: This implementation method is a trajectory data privacy protection method based on Venn diagram and differential privacy. The specific process is as follows:

[0060] Step 1: Get the friend users of user A whose trajectory is to be protected, and discretize the coordinates of the locations on each good user's trajectory into the geographic space after grid division;

[0061] Among them, the location coordinates on each trajectory are a point on the geographic space grid;

[0062] Step 2: Get the location coordinate set F contained in the trajectory of the i-th friend user i =(x i,1 ,x i,2 ,x i,n ,....,x i,N );

[0063] Among them, F i is the set of location coordinates contained in the trajectory of the i-th friend user, x i,n is the coordinates of n locations on the trajectory of the i-th friend user; N is the total number of locations on the trajectory of the i-th friend user;

[0064] Step 3: Get the set F1, ...F i , ..., F s The intersection C of the points in the intersection C is obtained by performing privacy protection on the location coordinates. The trajectory of user A after privacy protection is obtained as follows:

[0065] Step 31: Get the set F1, ...F i , ..., F s The intersection C:

[0066]

[0067] Among them, F s is the sth friend user of user A, s is the total number of friends of A, is the coordinate of the i*th location in the intersection C, is the coordinate of the N*th location in the intersection C, where N* is the total number of locations in the intersection C;

[0068] Step 32: Take the coordinates of each location in the intersection C as the center of the circle, draw a circle with r as the radius to obtain a circular area, and obtain the utility value of each location in each circular area. Based on the utility value of each location in the circular area, obtain the location coordinates of each obfuscated circle center position, and publish the trajectory of user A after privacy protection:

[0069] Step 321: Initialize i=1;

[0070] Step 322: As the center of the circle, draw a circle with r as the radius to obtain the circular area, and initialize The location number j in the inner part is 1;

[0071] Step 323: Get The location within the circular area with the center being The utility value

[0072]

[0073] in, So is the coordinate of the jth location in the circular area with centered on the circle, Yes To point The Euclidean distance, k is The total number of locations within the circular area with being the center;

[0074] Step 324: Based on the results obtained in step 323 Get The probability of being the center of the circle

[0075] As The probability of the center of the circle is as follows:

[0076]

[0077] Where ΔU is the sensitivity set to 1, ε is the privacy budget parameter, yes As The probability of the center of the circle;

[0078] Step 325: Determine whether j is equal to k. If j < k, set j = j + 1 and return to step 323; if j = k, set The location corresponding to the maximum value is The center of confusion;

[0079] Where k is Total number of locations within

[0080] Step 326: Determine whether i* is less than N*. If i<N*, set i*=i*+1 and return to step 322; if i*=N*, output the privacy-protected trajectory of user A composed of all the confusion circle centers and publish it.

[0081] Specific implementation method 2: A trajectory data privacy protection system based on Venn diagram and differential privacy, comprising: a friend user trajectory location coordinate acquisition module, a friend user trajectory intersection acquisition module, a confusion circle center location acquisition module, and a user trajectory generation module after privacy protection;

[0082] The friend user trajectory location coordinate acquisition module is used to obtain the location coordinates in the friend user trajectory of the to-be-protected trajectory user A, and discretize the location coordinates into the geographic space after grid division, and obtain the location coordinate set F contained in the i-th friend user trajectory of user A i =(x i,1 ,x i,2 ,x i,n ,....,x i,N );

[0083] Among them, F i is the set of location coordinates contained in the trajectory of the i-th friend user, x i,n is the coordinates of n locations on the trajectory of the i-th friend user; N is the total number of locations on the trajectory of the i-th friend user;

[0084] The friend user trajectory intersection acquisition module obtains the intersection C of the location coordinate sets in all friend user trajectories of user A, specifically:

[0085]

[0086] Among them, s is the total number of user A’s friends. is the coordinate of the i*th location in the intersection C, is the coordinate of the N*th location in the intersection C, where N* is the total number of locations in the intersection C;

[0087] The confusion center location acquisition module is used to draw a circle with each location in the intersection C as the center, and obtain the confusion center location of each circle, specifically:

[0088] S1. Initialize the friend user number i of user A = 1;

[0089] S2. As the center of the circle, draw a circle with r as the radius to obtain the circular area And initialize The location number j in the inner part is 1;

[0090] S3, Get Point The utility value Specifically:

[0091]

[0092] in, Yes To point The Euclidean distance of Total number of locations within

[0093] in, yes The j-th location coordinates within;

[0094] S4, point-based The utility value Get The probability of being the center of the circle Specifically:

[0095]

[0096] Where ΔU is the sensitivity, ε is the privacy budget parameter, yes As The probability of the center of the circle;

[0097] S5. Determine whether j is equal to k. If j < k, set j = j + 1 and return to S3. If j = k, set The location corresponding to the maximum value is The center of confusion;

[0098] Where k is Total number of locations within

[0099] S6, determine whether i* is less than N*, if i*<N*, set i*=i*+1, and return to step S2; if i*=N*, output all the confusion circle centers;

[0100] The privacy-protected user trajectory generation module uses each confusion circle center location to compose the privacy-protected trajectory of user A and publishes it.

[0101] Embodiment: In order to verify the beneficial effects of the present invention, the following experiments were carried out in this embodiment:

[0102] (1) This experiment sets the attack model as a background knowledge attack model: Assume that the attacker knows that Alice, John, and Eric are good friends through background knowledge, and knows the trajectory data of Alice and John. By calculating the same trajectory points of Alice and John, the trajectory data set of Alice, John, and Eric is inferred as shown in Table 1:

[0103] Table 1 Trajectory dataset

[0104]

[0105] (2) Divide the geographic space into grids to ensure that each location point in the trajectory data set is in the grid location point: discretize the GPS points of Alice's trajectory data into the coordinates of the location points in the grid-divided geographic space; discretize the GPS points of John's trajectory data into the coordinates of the location points in the grid-divided geographic space. The grid division result of the geographic space is as follows: Figure 1 As shown in the figure, the attack model uses the relationship between the Venn diagram set to calculate the set of repeated location points of Alice and John, and obviously infers Eric's trajectory data, resulting in the leakage of sensitive information, such as Figure 2 As shown;

[0106] The attack model uses the relationship between the Venn diagram set to calculate the set of repeated location points of Alice and John:

[0107] C=A∩B=(school, shopping mall, company)

[0108] A=(school, restaurant, shopping mall, company, home, playground)

[0109] B=(Company, School, Stadium, Shopping Mall, Hospital, Pet Shop)

[0110] (3) This embodiment uses the differential privacy exponential mechanism to perform privacy protection processing on repeated location coordinate point sets according to the method described in the specific implementation mode, specifically:

[0111] In a circular area with the repeated position coordinate point as the center and r as the radius, for each position point coordinate in the repeated position coordinate point set, calculate its utility value function;

[0112] The utility value function is the coordinate value of each position point in the circular area To the center point of the circle The Euclidean distance between The location within the circular area with the center being The utility value

[0113]

[0114] Confusing circle center position coordinate point Probability:

[0115]

[0116] Where ε is the privacy budget parameter;

[0117] Obtain the location coordinates of each repeated location coordinate point by the above method, so as to publish the trajectory data processed with privacy protection, such as Figure 3 shown.

[0118] According to the above experiments, the present invention can protect the privacy of the user's trajectory, thereby preventing the attack model from using background knowledge to infer individual sensitive information.

Claims

1. A trajectory data privacy protection method based on Venn diagram and differential privacy, characterized in that The specific process of the method is: Step 1: Obtain the friend users of user A whose trajectory is to be protected, and discretize the coordinates of the locations on each friend user's trajectory into the geographic space after grid division; Step 2: Get the location coordinate set F contained in the trajectory of user A’s i-th friend i =(x i,1 ,x i,2 ,x i,n ,....,x i,N ); Among them, F i is the set of location coordinates contained in the trajectory of the i-th friend user, x i,n is the coordinates of n locations on the trajectory of the i-th friend user; N is the total number of locations on the trajectory of the i-th friend user; Step 3: Obtain the intersection C of the location coordinate sets in the trajectories of all friend users of user A, and perform privacy protection on the location coordinates in the intersection C to obtain the trajectory of user A after privacy protection.

2. The method for protecting privacy of trajectory data based on Venn diagram and differential privacy according to claim 1, characterized in that: In step 3, the intersection C of the location coordinates of all the friend user trajectories of user A is obtained, and the location coordinates in the intersection C are privacy protected to obtain the trajectory of user A after privacy protection, specifically: Step 31: Get the intersection C of the location coordinates of all friend user trajectories of user A: Among them, s is the total number of user A’s friends. is the coordinate of the i*th location in the intersection C, is the coordinate of the N*th location in the intersection C, where N* is the total number of locations in the intersection C; Step 32: Use intersection C to obtain the trajectory of user A after privacy protection.

3. The method for protecting privacy of trajectory data based on Venn diagram and differential privacy according to claim 2, characterized in that: The trajectory of user A after privacy protection is obtained by using the intersection C in step 32, specifically: Step 321: Initialize user A's friend user number i=1; Step 322: As the center of the circle, draw a circle with r as the radius to obtain the circular area And initialize The location number j in the inner part is 1; Step 323: Get points The utility value in, yes The j-th location coordinates within; Step 324: Utilization Point The utility value Get The probability of being the center of the circle Step 325: Determine whether j is equal to k. If j < k, set j = j + 1 and return to step 323; if j = k, set The location corresponding to the maximum value is The center of confusion; Where k is Total number of locations within Step 326: Determine whether i* is less than N*. If i*<N*, set i*=i*+1 and return to step 322; if i*=N*, output all the confusion circle centers, the privacy-protected trajectory of user A composed of all the confusion circle centers, and publish the privacy-protected trajectory of user A.

4. The method for protecting privacy of trajectory data based on Venn diagram and differential privacy according to claim 3, characterized in that: The acquisition point in step 323 The utility value Specifically: in, Yes To point The Euclidean distance of The total number of locations within.

5. The method for protecting privacy of trajectory data based on Venn diagram and differential privacy according to claim 4, characterized in that: The point-based The utility value Get The probability of being the center of the circle Specifically: Where ΔU is the sensitivity, ε is the privacy budget parameter, yes As The probability of the center of the circle.

6. A trajectory data privacy protection system based on Venn diagram and differential privacy, characterized in that The system includes: a friend user trajectory location coordinate acquisition module, a friend user trajectory intersection acquisition module, a confusion circle center location acquisition module, and a privacy-protected user trajectory generation module; The friend user trajectory location coordinate acquisition module is used to obtain the coordinates of the locations contained in the friend user trajectory of the to-be-protected trajectory user A, and discretize the location coordinates into the geographic space after grid division, to obtain the location coordinate set F contained in the i-th friend user trajectory of user A i =(x i,1 ,x i,2 ,x i,n ,....,x i,N ); Among them, F i is the set of location coordinates contained in the trajectory of the i-th friend user, x i,n is the coordinates of n locations on the trajectory of the i-th friend user; N is the total number of locations on the trajectory of the i-th friend user; The friend user trajectory intersection acquisition module acquires the intersection C of the location coordinate sets in all friend user trajectories of user A; The confusion center location acquisition module is used to draw a circle with each location in the intersection C as the center, and obtain the confusion center of each circle; The privacy-protected user trajectory generation module uses the location corresponding to each confusion circle center to compose the privacy-protected trajectory of user A and publishes it.

7. The trajectory data privacy protection system based on Venn diagram and differential privacy according to claim 6, characterized in that: The friend user trajectory intersection acquisition module obtains the intersection C of the location coordinate sets in all friend user trajectories of user A, specifically: Among them, s is the total number of user A’s friends. is the coordinate of the i*th location in the intersection C, is the coordinate of the N*th location in the intersection C, and N* is the total number of locations in the intersection C.

8. The trajectory data privacy protection system based on Venn diagram and differential privacy according to claim 7, characterized in that: The confusion center location acquisition module is used to draw a circle with each location in the intersection C as the center, and obtain the confusion center of each circle, specifically: S1. Initialize the friend user number i of user A = 1; S2. As the center of the circle, draw a circle with r as the radius to obtain the circular area And initialize The location number j in the inner part is 1; S3, Get Point The utility value in, yes The j-th location coordinates within; S4, point-based The utility value Get The probability of being the center of the circle S5. Determine whether j is equal to k. If j < k, set j = j + 1 and return to S3. If j = k, set The location corresponding to the maximum value is The center of confusion; Where k is Total number of locations within S6. Determine whether i* is less than N*. If i*<N*, set i*=i*+1 and return to step S2; if i*=N*, output all the confusion circle centers.

9. The trajectory data privacy protection system based on Venn diagram and differential privacy according to claim 8, characterized in that: The acquisition point in S3 The utility value Specifically: in, Yes To point The Euclidean distance of The total number of locations within.

10. The trajectory data privacy protection system based on Venn diagram and differential privacy according to claim 9, characterized in that: The point-based The utility value Get The probability of being the center of the circle Specifically: Where ΔU is the sensitivity, ε is the privacy budget parameter, yes As The probability of the center of the circle.

Citation Information

Patent Citations

  • Methods for the augmentation, exploration, and maintenance of project hierarchies

    CN109121436A

  • Processing method and processing device for position data for resisting speculative attacks in LBS

    CN110602631A

  • Track privacy protection method and device based on differential privacy

    CN112069532A

  • System and Method for Extremely Efficient Image and Pattern Recognition and Artificial Intelligence Platform

    US20180204111A1

  • Systems, methods, and media for evaluation of trajectories and selection of a trajectory for a vehicle

    US20220219726A1