Geographic position data perturbation method based on localized differential privacy

By performing instant disturbance processing on user equipment, using the concepts of core privacy areas, expected disturbance areas and peripheral privacy areas, the impact of localized differential privacy solutions on data utility is solved, and data accuracy is maintained while protecting user privacy The balance of the location services has promoted the development of location services.

CN118981793APending Publication Date: 2024-11-19NANJING UNIV OF POSTS & TELECOMM
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411121282.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

Existing localized differential privacy schemes may affect data utility when disturbing location data, resulting in a decline in service quality and making it difficult to find a balance between protecting user privacy and maintaining data accuracy.

Method used

Real-time perturbation processing is performed on user equipment. By setting the core privacy area, the expected perturbation area and the peripheral privacy area, the perturbation probability density function is calculated, and random noise is added to protect the location data to ensure that the real location is not leaked.

Benefits of technology

While protecting user privacy, it reduces the negative impact on location data accuracy and service quality, provides a more reliable privacy protection mechanism, enhances users' sense of trust in the use of location data, and promotes the development of location services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118981793A_ABST
    Figure CN118981793A_ABST
Patent Text Reader

Abstract

The invention discloses a geographical location data perturbation method based on localized differential privacy. The method comprises the following steps: S1, a client collects location information of a user; s2, setting a radius r3 of a peripheral privacy area of a parameter, wherein the radius r3 represents the maximum range of disturbance; s3, a privacy parameter epsilon of localized differential privacy is determined, the privacy parameter epsilon controls the disturbance intensity and the privacy protection level, and the radius r1 of a core privacy area and the radius r2 of an expected disturbance area are determined; defining three areas, wherein r < = r1 is a core privacy area, and r1lt is a core privacy area; r < = r2 is an expected disturbance area, r2lt; r < = r3 is a peripheral privacy area; s4, calculating a disturbance probability density function p (r) according to the parameters r1, r2, r3 and epsilon; s5, independently carrying out data disturbance on the equipment of the user; and S6, issuing the disturbed data. The method can be widely applied to various scenes needing to protect the privacy of the user, and meets the requirements of relevant privacy protection laws and regulations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of data privacy protection and location service, and more specifically, relates to a geographic location data perturbation method based on localized differential privacy. Background Art

[0002] With the popularization of smart devices and the rapid development of location services, the collection and use of user geographic location data has become more and more common. These data play an important role in traffic management, social networks, emergency services, personalized advertising and other fields. However, the sensitivity of location data has also caused people to worry about the leakage of personal privacy. The existing differential privacy (DP) technology has achieved remarkable results in protecting user privacy. Differential privacy protects user privacy by introducing random noise in data release or calculation results, making the data of a single user difficult to identify and reconstruct. However, traditional differential privacy methods are mainly used in data aggregation and data release scenarios, and have certain limitations in protecting real-time individual location data.

[0003] Localized Differential Privacy (LDP) is a variant of differential privacy that has significant advantages in protecting real-time location data. First, localized differential privacy perturbs data at the source of data collection (i.e., user devices), so users do not have to trust the data collector. Even if the data collector is malicious, it cannot obtain the user's real data. Second, localized differential privacy is suitable for the protection of real-time data. The user's data is perturbed when it is generated, and privacy protection can be provided immediately. It is suitable for various application scenarios of real-time data collection and processing, such as location services and sensor data collection.

[0004] Although localized differential privacy has significant advantages in privacy protection, existing localized differential privacy schemes may seriously affect the utility of data when perturbing data, resulting in a decrease in service quality. For example, when the perturbation intensity is too large, the perturbed location data may deviate far from the user's true location, thereby affecting the accuracy of location services and user experience. Therefore, how to maintain the utility of data while protecting user privacy is an important issue that localized differential privacy needs to solve.

[0005] Therefore, it is urgent to design a geolocation data perturbation method based on localized differential privacy. Summary of the invention

[0006] The present invention aims to solve the privacy leakage problem existing in traditional location data processing methods and improve the challenges that may affect data utility in existing localized differential privacy schemes. With the popularization of mobile Internet and location services, users' location information is collected and used more and more frequently, but this also brings serious privacy risks. Traditional data protection methods often face difficult problems in protecting user privacy: the balance between protecting privacy and maintaining data utility.

[0007] Therefore, the present invention aims to provide a new location data processing method, which performs instant disturbance processing on location data at the source of user data generation (i.e., user device), thereby protecting user privacy and minimizing the negative impact on data utility.

[0008] The present invention aims to achieve the following goals: protect user privacy, perturb the user's location data at the source of data collection, and ensure that the user's real location information is not leaked or identified; improve data utility, through reasonable perturbation settings and privacy protection strategies, minimize the impact on location data accuracy and service quality, and maintain the practicality and effectiveness of data; promote the development of location services, provide a reliable privacy protection mechanism for location services, enhance users' trust in the use of location data, and thus promote the development and innovation in the field of location services.

[0009] Professional terms and their constraints:

[0010] Privacy budget: The privacy budget is a parameter that controls the strength of data privacy protection, which is defined by the user and is represented by ε in this invention.

[0011] Local differential privacy: It is a privacy protection technology that allows data to be processed for privacy protection before collection, thereby ensuring the privacy and security of the data. Compared with global differential privacy, the main difference of LDP is that it adds noise directly to individual data points instead of adding it to the query results after data aggregation.

[0012] The technical solution to achieve the purpose of the present invention is to provide a method for perturbing geographic location data based on localized differential privacy, comprising the following steps:

[0013] S1. The local client collects the user's location information.

[0014] S2. Set the parameter outer privacy zone radius r3, which represents the maximum range of the disturbance.

[0015] S3. Determine the privacy parameter ∈ of local differential privacy, which controls the intensity of perturbation and the level of privacy protection. Also determine the radius r1 of the core privacy area and the radius r2 of the expected perturbation area. These two parameters control the approximate range of perturbation. We define three regions: r ≤ r1 is the core privacy area (Region A), r1 < r ≤ r2 is the expected perturbation area (Region B), and r2 < r ≤ r3 is the peripheral privacy area (Region C).

[0016] S4. Calculate its perturbation probability density function p(r) according to the parameters r1, r2, r3, ∈. The probability that the original point is perturbed to the expected perturbation area is the highest, and the probability of being perturbed to any point in the core privacy area and the peripheral privacy area is much lower than the probability of being perturbed to any point in the expected perturbation area.

[0017] S5. Independently perform data perturbation on the user's device, and add random noise to the location data according to the calculated perturbation probability.

[0018] S6. Publish the perturbed data to ensure that even if the attacker has information about all other data points, they cannot accurately infer the true location information of any individual.

[0019] Furthermore, in step S1, the collected location information should be stored in a standardized format, such as (latitude, longitude, time), where latitude and longitude represent the latitude and longitude of the user's location respectively, and time represents the timestamp.

[0020] In step S2, a suitable value of r3 needs to be selected. This value should be large enough to cover most of the possible activity ranges of the user, usually 15 - 30 km, while ensuring the effectiveness of privacy protection.

[0021] In step S3, first determine the privacy parameter ∈ of local differential privacy. r1 defines the radius of the core privacy area and should be selected according to the sensitivity of the data and the actual needs of the user. This value should be small enough to cover the area where the user does not want to be accurately located. For example, if the client does not want to expose the specific room location where they are, then r1 is set to about 100 m. r2 defines the radius of the expected perturbation area. When setting r3, the privacy protection requirements of the application scenario should be considered, and the user's expectation for the privacy of location data should be determined to select a suitable value.

[0022] Furthermore, the specific steps of S4 are as follows:

[0023] S4-1. This solution hopes that the probability of the perturbation result in the expected perturbation area is greater than that in the core privacy area and the peripheral privacy area. To meet the definition of local differential privacy and the expectation for the perturbation result, the probability ratio of the three regions is designed: Core area (Region A): r ≤ r1

[0024] The probability of a disturbance at any point in this region is the probability of a disturbance at any point in region C. times.

[0025] Expected disturbance area (area B): r1 <r≤r2

[0026] The probability of a disturbance at any point in this region is the probability of a disturbance at any point in region C. Peripheral privacy area (area C): r2 <r≤r3

[0027] The probability of disturbance at any point in this region is pc.

[0028] S4-2. Then we solve the probability density function p(r) of the entire area according to the normalization condition. p(r) is a piecewise function about r:

[0029]

[0030] According to the normalization condition

[0031]

[0032] According to the above two formulas, we can calculate

[0033]

[0034] So we conclude:

[0035] Probability density function of the core area:

[0036] Probability density function of the expected disturbance area:

[0037] Probability density function of the peripheral privacy area: p C (r) = p C .

[0038] Furthermore, in step S5, data perturbation is independently performed on the user's device, and random noise is added to the location data according to the calculated perturbation probability; specifically:

[0039] S5-1. First calculate the probability of disturbance to three regions

[0040] Expressed using known parameters:

[0041]

[0042] S5-2. Generate a random number u between 0 and 1, and randomly select an angle θ from 0 to 2π; if u <PA It represents the situation of the perturbation in the core area. Then, a radius r is uniformly selected within the radius r1; if P A ≤u≤P A +P B It represents the situation of the perturbation in the expected perturbation area. Then, a radius r is uniformly selected within the range from r2 to r3; if P A +P B <u≤1 represents the situation of the perturbation in the peripheral privacy area. Then, a radius r is uniformly selected within the range from r2 to r3;

[0043] S5-3. Convert the radius r into the unit of longitude and latitude coordinates; add noise to the location information to change the original (latitude, longitude, time) to (latitude + r * sinθ, longitude + r * cosθ, time).

[0044] According to another aspect of the present invention, there is provided a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the method for perturbing geographical location data based on local differential privacy of the present invention are implemented.

[0045] According to still another aspect of the present invention, there is provided a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps in the method for perturbing geographical location data based on local differential privacy of the present invention are implemented.

[0046] Compared with the prior art, the present invention has at least the following beneficial effects:

[0047] The present invention not only aims to solve the problem of balancing privacy protection and data utility in traditional location data processing methods, but also provides a safer and more reliable location service experience for users through innovative technical means, setting a new benchmark for data privacy protection in the mobile Internet era. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments will be briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present invention and do not limit the present invention.

[0049] Figure 1 is a flowchart of a preferred embodiment of the present invention;

[0050] Figure 2 is a schematic diagram of different regions in the perturbation method of a preferred embodiment of the present invention;

[0051] Figure 3It is a flow chart of a method for adding noise to a position point in a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0052] To make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them.

[0053] Unless otherwise defined, technical or scientific terms used herein shall have the same meaning as commonly understood by one of ordinary skill in the art to which the invention belongs.

[0054] The following is combined with Figure 1-3 The specific embodiments of the present invention are described in detail with examples.

[0055] Example 1: Figure 1-3 As shown, the present invention provides the following technical solution: a geographic location data perturbation method based on localized differential privacy,

[0056] S1. First, the local client collects the user's location information. This embodiment perturbs two location points. (32.0615513, 118.7915619, 2024-7-19) (32.1135405, 118.9308186, 2024-7-19)

[0057] S2. Set the parameter outer privacy zone radius r3, which indicates the maximum range of disturbance. We set r3 to 30km, which means the maximum disturbance radius of these two points is 30km.

[0058] S3-1. First, determine the privacy parameter ∈=10 of localized differential privacy. In geographic differential privacy protection, this parameter controls the intensity of disturbance and the level of privacy protection. Preliminary calculations show that when ∈ is in the range of 10 to 15, it can bring better utility and privacy protection effects.

[0059] S3-2. Set the core privacy zone radius r1. r1 represents the privacy radius that the user does not want to expose. In this scenario, it is set to 100m, indicating that the user does not want to expose the location information within a radius of 100m, and the probability of disturbing this area is low. Then set the expected disturbance area radius r2. r2 represents the radius range that the user expects to disturb. In this scenario, we set it to 2km, indicating that we hope that the disturbance point will fall within the range of 100m-2km from the original point with a greater probability.

[0060] S4. First, according to the set parameters r1 = 100m, r2 = 2000m, r3 = 30000m, ∈ = 10, substitute the following formula for solution. The probability of disturbance to three different areas is obtained.

[0061]

[0062] Finally, we solve P A =0.00467, P B =0.985, P C =0.0195.

[0063] S5. First, add noise to the first position point, generate a random number u=0.50631472 between 0 and 1, and randomly select an angle θ=4.61827004 from 0 to 2π. A ≤u≤P A +P B , which represents the disturbance in area B, then a radius r is uniformly selected from the range of r1 to r2, that is, a random number 1313 is generated in the range of 100-2000. Finally, the radius r is converted into the unit of longitude and latitude coordinates, 1313m≈0.0118 degrees. The location information is denoised to convert the original (latitude, longitude, time) into (latitude+r*sinθ, longitude+r*cosθ, time), that is, (32.0615513+0.0118sin4.618,118.7915619+0.0118cos4.618, 2024-7-19). The final result is (32.0498038,118.7904500, 2024-7-19).

[0064] Raw data (32.0615513,118.7915619,2024-7-19) Noised data (32.0498038,118.7904500,2024-7-19)

[0065] Then, the second position point is noised to generate a random number u=0.99116515 between 0 and 1, and the angle θ=1.61266704 is randomly selected from 0 to 2π. A +P BWhen u ≤ 1, which represents the situation of the perturbation in region C, then a radius r is uniformly selected within the range from r2 to r3, that is, a random number 5075.03949677 is generated between 2000 and 30000. Finally, the radius r is converted into the unit of longitude and latitude coordinates, and 5075m ≈ 0.045 degrees. Noise is added to the location information, that is, (32.1135405 + 0.0456 * sin1.612667, 118.9308186 + 0.0456 * cos1.612667, 2024 - 7 - 19). The final result is (32.1591187, 118.9294359, 2024 - 7 - 19).

[0066] (32.1135405,118.9308186,2024-7-19) Noised data (32.1591187,118.9294359,2024-7-19)

[0067] S6. Finally, the perturbed data is published to the server.

[0068] Example 2:

[0069] The computer-readable storage medium of this embodiment stores a computer program, and when the program is executed by a processor, it implements the steps in the method for perturbing geographical location data based on local differential privacy in Example 1.

[0070] The computer-readable storage medium of this embodiment can be the internal storage unit of the terminal, such as the hard disk or memory of the terminal; the computer-readable storage medium of this embodiment can also be the external storage device of the terminal, such as the plug-in hard disk, smart memory card, secure digital card, flash card, etc. equipped on the terminal; further, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the terminal.

[0071] The computer-readable storage medium of this embodiment is used to store the computer program and other programs and data required by the terminal, and the computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.

[0072] Example 3:

[0073] The computer device of this embodiment includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the steps of the method for perturbing geographical location data based on local differential privacy in Example 1.

[0074] In this embodiment, the processor may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, readily available programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0075] Those skilled in the art will appreciate that the disclosed content of the embodiments may be provided as methods, systems, or computer program products. Therefore, the present solution may adopt the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Moreover, the present solution may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program codes.

[0076] The present solution is described with reference to the method according to the embodiment of the present solution and the flowchart and / or block diagram of the computer program product. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions; these computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 one or more processes and / or methods Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0077] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 one or more processes and / or methods Figure 1 A function specified in one or more boxes.

[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 one or more processes and / or methods Figure 1A step that specifies a function in one or more boxes.

[0079] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0080] The examples described in the present invention are merely descriptions of the preferred implementation modes of the present invention, and are not intended to limit the concept and scope of the present invention. Without departing from the design concept of the present invention, various modifications and improvements made to the technical solutions of the present invention by engineers and technicians in this field should all fall within the protection scope of the present invention.

Claims

1. A geographic location data perturbation method based on localized differential privacy, characterized in that: It includes the following steps: S1. The local client collects the location information of the user; S2. Set the parameter of the peripheral privacy area radius r3, which represents the maximum range of perturbation; S3. Determine the privacy parameter ∈ of local differential privacy. The privacy parameter ∈ controls the intensity of perturbation and the level of privacy protection, and determine the core privacy area radius r1 and the expected perturbation area radius r2; Define three areas, r ≤ r1 is the core privacy area, r1 < r ≤ r2 is the expected perturbation area, and r2 < r ≤ r3 is the peripheral privacy area; S4. According to the parameters r1, r2, r3, ∈, calculate its perturbation probability density function p(r); S5. Independently perform data perturbation on the user's device, and add random noise to the location data according to the calculated perturbation probability; S6. Publish the perturbed data to ensure that even if the attacker has the information of all other data points, the true location information of any individual cannot be accurately inferred.

2. The method according to claim 1, characterized in that In step S1, the collected location information should be stored in a standardized format, and the format is latitude, longitude and time, where latitude and longitude represent the latitude and longitude of the user's location respectively, and time represents the timestamp.

3. The method according to claim 1, characterized in that The specific steps of S4 are as follows: S4-1. In order to meet the definition of local differential privacy and the expectation for the perturbation result, design the probability ratio of the three areas: Core area: r ≤ r1; The probability of disturbance at any point in the core area is the probability of disturbance at any point in the peripheral privacy area. times; Expected perturbation area: r1 < r ≤ r2; The probability of disturbance at any point in the expected disturbance area is the probability of any point in the peripheral privacy area. times; Peripheral privacy area: r2 < r ≤ r3; The perturbation probability of any point in the peripheral privacy area is pc; S4-2. Solve the probability density function p(r) of the whole area according to the normalization condition. p(r) is a piecewise function of r: According to the normalization condition Substitute and calculate according to the above two formulas So it is obtained that: Probability density function of the core area: Probability density function of the expected disturbance area: Probability density function of the peripheral privacy area: p C (r) = p C .

4. The method according to claim 2, characterized in that: In step S5, independently perform data perturbation on the user's device, and add random noise to the location data according to the calculated perturbation probability; specifically: S5-1. First calculate the probability of disturbance to three regions Represented by known parameters: S5-2. Generate a random number u between 0 and 1, and randomly select an angle θ from 0 to 2π; if u < P A It represents the situation of perturbation in the core area, then randomly select a radius r uniformly within the radius r1; if P A ≤u≤P A +P B It represents the situation of perturbation in the expected perturbation area, then randomly select a radius r uniformly within the range from r2 to r3; if P A +P B <u≤1 represents the situation of perturbation in the peripheral privacy area, then randomly select a radius r uniformly within the range from r2 to r3; S5-3. Convert the radius r into the unit of latitude and longitude coordinates; add noise to the location information to change the original (i = latitude, longitude, time) to (latitude + r * sinθ, longitude + r * cosθ, time).

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by the processor, it implements the steps in the method for perturbing geographical location data based on local differential privacy described in any one of claims 1 to 4.

6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the steps in the method for perturbing geographical location data based on local differential privacy described in any one of claims 1 to 4.