CN109104696B - Track privacy protection method and system for mobile user based on differential privacy - Google Patents
Track privacy protection method and system for mobile user based on differential privacy Download PDFInfo
- Publication number
- CN109104696B CN109104696B CN201810916399.6A CN201810916399A CN109104696B CN 109104696 B CN109104696 B CN 109104696B CN 201810916399 A CN201810916399 A CN 201810916399A CN 109104696 B CN109104696 B CN 109104696B
- Authority
- CN
- China
- Prior art keywords
- time
- user
- privacy
- base station
- data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000006854 communication Effects 0.000 claims abstract description 82
- 238000004891 communication Methods 0.000 claims abstract description 81
- 230000002776 aggregation Effects 0.000 claims abstract description 18
- 238000004220 aggregation Methods 0.000 claims abstract description 18
- 230000007246 mechanism Effects 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 9
- 241000282414 Homo sapiens Species 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000011282 treatment Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04K—SECRET COMMUNICATION; JAMMING OF COMMUNICATION
- H04K3/00—Jamming of communication; Counter-measures
- H04K3/80—Jamming or countermeasure characterized by its function
- H04K3/82—Jamming or countermeasure characterized by its function related to preventing surveillance, interception or detection
- H04K3/825—Jamming or countermeasure characterized by its function related to preventing surveillance, interception or detection by jamming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/003—Locating users or terminals or network equipment for network management purposes, e.g. mobility management locating network equipment
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a track privacy protection method of a mobile user based on differential privacy, which is applied to a server and acts on m communication base stations L ═ L1,l2,…lmN users U ═ U1,u2，…unIn a moving scene, where liIt represents the position of the ith communication base station, i is more than or equal to 1 and less than or equal to m; u. ofjRepresenting the jth user, j is more than or equal to 1 and less than or equal to n, the method comprises the following steps: s1, initializing; s2, a data aggregation stage; s3, a data disturbance stage; s4, data release phase. The invention also discloses a track privacy protection system of the mobile user based on the differential privacy. According to the invention, the number of the users covered by the communication base station is disturbed, and the disturbance is carried out on the position of each user in the case of other schemes, so that the use of privacy budget is greatly reduced, the usability of data is ensured, and the calculation cost is reduced.
Description
Technical Field
The invention relates to the technical field of network and information security, in particular to a track privacy protection method and system for a mobile user based on differential privacy.
Background
With the rapid development of internet technology, a big data age has come, and the popularization of mobile devices has enabled human mobile data to be widely collected through cellular networks and mobile applications and publicly released for academic research and business purposes. However, one of the main problems with such data distribution is how to protect the privacy of the mobile user.
To protect the privacy of the users, the data owner (operator) would only publish aggregated mobile data, rather than providing a track record for each user, e.g. publishing the number of users in the coverage of the base station within a specific time stamp. The aggregated user mobile statistical data has great practical value in a plurality of applications such as traffic scheduling and business intelligence. More importantly, most of these data providers consider that such aggregated statistics can protect the privacy of users by publishing them, since an adversary cannot distinguish a particular user from the aggregated data.
Recent research has shown that publishing aggregated user mobility statistics may lead to privacy leakage in their movement trajectories, mainly because of two key features present in human movement. First, the movement pattern of a single user is consistent and regular, which makes the trajectory for a single user highly predictable. Second, the movement pattern of any one user is significantly different from the movement patterns of other users, which enables an adversary to specifically re-recognize the trajectory of a certain user. Although it is difficult to distinguish the record of each user from the aggregated data under a certain timestamp, the motion trajectory of the user can be recovered from the aggregated data according to the movement characteristics of the user in continuous time, and then the motion trajectory of a specific user can be obtained again. It is crucial to effectively protect the privacy of the trajectory of the mobile device user.
Disclosure of Invention
The invention aims to provide a track privacy protection method and a track privacy protection system for a mobile user based on differential privacy, which protect the position privacy of the user by using a Laplace mechanism in the differential privacy, thereby preventing the recovery of the moving track of an adversary with any background knowledge to the user.
The invention is realized by the following technical scheme: a track privacy protection method of a mobile user based on differential privacy is applied to a server and acts on m communication base stations L ═ L1,l2,…lmN users U ═ U1,u2,…unIn a moving scene, where liIt represents the position of the ith communication base station, i is more than or equal to 1 and less than or equal to m; u. ofjRepresents the jth user, 1 ≦ j ≦ n, theThe method comprises the following steps:
s1, initialization stage: when user ujInto a communication base stationiThe server of the communication operator records the relevant information of the user: the anonymized user ID number, the accessed communication base station position information and the access time t;
s2, data aggregation stage: the server carries out statistical aggregation on the relevant information of the users collected within a period of time according to a certain time interval, extracts the position information of the communication base station with the most frequent access of each user within each time period, and calculates the total number of the users contained in each communication base station within the time period
Represents the communication base station l at time tiI is more than or equal to 1 and less than or equal to m;
s3, data disturbance stage: time is divided into a day time zone, a night time zone and a late night time zone according to the movement characteristics of a human being, by
Calculating the distribution of the number of people in each base station in each time period
Reference differential privacy mechanism to data in these three time periods
Carrying out different disturbance treatments;
s4, data release stage: the communication operator will process the data
And releasing the message.
As one of the preferable embodiments of the present invention, the data aggregation stage of step S2 specifically includes the following operation flows:
(1) time period division: dividing according to different time intervals according to the requirement on the resolution of the user moving track, wherein the larger the time interval is, the smaller the resolution of the user moving track is; the smaller the time interval is, the more accurate the user movement track is;
(2) position extraction: after the time interval is divided, a user can have 1 or more access records of different communication base stations in a certain time interval, and at the moment, the base station which is most frequently accessed by the user in the communication base stations is extracted as the position accessed by the user in the time period;
(3) and (3) data statistics: through step (2), it can be known that the user can only access one communication base station under each time stamp, so that each base station (l) under the time stamp t is calculated1,l2,…lm) Number of visits to users in a coverage area
Thereby, the distribution of the number of users in the coverage area of each communication base station in a certain area, namely, the data set under the real-time condition can be obtained
As one of the preferable embodiments of the present invention, the data perturbation phase of step S3 specifically includes:
(1) in the daytime, the access position of the base station of the user is in a state of continuous updating and changing from 7 am to 6 pm; at this time the data sets D of adjacent time instantst-1And DtThe number of users in the data set D is different, and the data set D is obtained at each timetDirect introduction of Laplace mechanism satisfying differential privacy to add perturbation noise conforming to Laplace distribution
(2) In the night time period, setting the time from 6 pm to 11 pm, the base station access position of the user is moreThe new speed is reduced; at this time the data sets D of adjacent time instantst-1And DtThe distribution of the number of users still has difference, but the difference is in the case of large or small;
(3) in the late-night time period, from 11 pm to 7 pm, the access location of the base station of the user will not change, and the data set D at the adjacent time ist-1And DtThe user distribution of (2) is almost unchanged; the track privacy of the user can be exposed only in the moving process, and the original data is directly published at the moment.
In a preferred embodiment of the present invention, in order to ensure that the total number n of base stations does not change, only the first m-1 base stations are disturbed in the step (1), and Noise vectors introduced by the first m-1 base stations are Noisem-1＝(x1,x2,…,xm-1) The noise added by the mth base station is the opposite number according to the noise added by the first m-1 base stations,
as one of preferable embodiments of the present invention, in the step (2): data set D at adjacent timet-1And DtIn the case of large user distribution difference, only the data set D at the current moment needs to be calculatedtAnd the data set D released at the previous momentt-1Comparing the distribution difference with a set fixed threshold value T, and judging whether to carry out disturbance processing on the current data set; thus only a part of the data set D need be addressedtAnd carrying out disturbance processing, and setting the number of the data sets D needing the disturbance processing as C.
As one of the preferable modes of the present invention, the following perturbation method is applied in the evening time period of the step (2), and the perturbation method comprises the following steps:
(1) and (3) privacy budget allocation: before disturbance processing is carried out on the data set D, firstly, the privacy budget is distributed, so that the privacy budget meets the requirement of differential privacy in the whole data disturbance processing stage; make ═ 11+2，1Is used for privacy budgeting in the decision process, an1＝k，2Is a privacy budget used in the perturbation process on the data set D;
(2) a judging stage: in the process, a Laplace mechanism meeting the difference privacy is adopted to add disturbance noise vectors conforming to Laplace distribution
Calculating a noise threshold
And the data set of the current time
And the data set released at the previous moment
Noise value of distribution difference between
(3) A disturbance stage: for the
Introducing a privacy budget of
Adopts a Laplace mechanism satisfying difference privacy to add disturbance noise conforming to Laplace distribution
Noisem-1＝(x1,x2,…,xm-1),
Computing a noisy data set
As one preferable aspect of the present invention, in the determination stage of the step (2): when in use
Then pair
Performing perturbation processing, otherwise
Instead of distributing the user's location at the current moment, i.e. publishing
As one preferable aspect of the present invention, in the perturbation phase of the step (3): when the privacy budget is remained, adding the noise of all the remained privacy budgets at the last moment; when privacy budgeting2When exhausted, the subsequent data set will be published with the last distributed data set.
The invention also discloses a track privacy protection system of the mobile user based on the differential privacy, which is applied to the server and acts on m communication base stations L ═ L1,l2,…lmN users U ═ U1,u2,…unIn a moving scene, where liIt represents the position of the ith communication base station, i is more than or equal to 1 and less than or equal to m; u. ofjRepresenting the jth user, j is more than or equal to 1 and less than or equal to n, the system comprises the following modules:
an initialization module: when user ujInto a communication base stationiFor recording the relevant information of the user by the server of the communication carrier: the anonymized user ID number, the accessed communication base station position information and the access time t;
a data aggregation module: the server carries out statistical aggregation on the user related information collected in a period of time according to a certain time intervalAnd combining, extracting the position information of the communication base station which is most frequently visited by each user in each time period, and calculating the total number of the users in each communication base station in the time period
Represents the communication base station l at time tiI is more than or equal to 1 and less than or equal to m;
a data perturbation module: for dividing time into a day time zone, a night time zone and a late night time zone according to the movement characteristics of human beings, and passing through
Calculating the distribution of the number of people in each base station in each time period
Reference differential privacy mechanism to data in these three time periods
Carrying out different disturbance treatments;
the data release module: for processing data of communication operator
And releasing the message.
Compared with the prior art, the invention has the advantages that:
(1) according to the invention, the number of the users covered by the communication base station is disturbed, and the disturbance is carried out on the position of each user in the case of other schemes, so that the use of privacy budget is greatly reduced, the usability of data is ensured, and the calculation cost is reduced;
(2) the invention provides the aggregated data information based on the communication base station for the first time, the moving track of the user is protected by using a differential privacy mechanism, and the introduced noise follows the principle that the total number of people covered by the communication base station is unchanged, so that the difficulty of recovering the user track by the adversary is increased;
(3) the invention relates to a method for acquiring a data set D according to adjacent moments in different time periodst-1And DtThe time is divided into a day time period, a night time period and a late night time period, and different disturbance processing is carried out on the three time periods by using a differential privacy mechanism.
Drawings
Fig. 1 is a schematic view of an application scenario of embodiment 1 of the present invention;
fig. 2 is a flowchart of main implementation steps of a track privacy protection method for a mobile user based on differential privacy according to embodiment 1 of the present invention;
fig. 3 is a diagram of an aggregated data distribution of the number of people covered by a communication base station at a certain time according to embodiment 1 of the present invention.
Detailed Description
The following examples are given for the detailed implementation and specific operation of the present invention, but the scope of the present invention is not limited to the following examples.
Example 1
Referring to fig. 1-3: in order to protect the track privacy of the user of the mobile device during the communication process from being leaked, the track privacy protection method for the mobile user based on the differential privacy of the embodiment is applied to the server and acts on m communication base stations L ═ L1,l2,…lmN users U ═ U1,u2,…unIn a moving scene, where liIt represents the position of the ith communication base station, i is more than or equal to 1 and less than or equal to m; u. ofjRepresents the jth user, j is more than or equal to 1 and less than or equal to n, when the user ujAt a base station liWill pass through base station liTransmitting signals to obtain related request services; the server in the background will collect the user ujThe method comprises the following steps:
s1, initialization stage: when user ujInto a communication base stationiThe server of the communication operator records the relevant information of the user: the anonymized user ID number, the accessed communication base station position information and the access time t; each user can be in the coverage range of a certain divided communication base station at any time, when the user needs to request service, the user can communicate with the base station, and the time base station can record the personal identity information, the position information and the time for accessing the communication base station and send the information to a background server;
s2, data aggregation stage: the server carries out statistical aggregation on the relevant information of the users collected within a period of time according to a certain time interval, extracts the position information of the communication base station with the most frequent access of each user within each time period, and calculates the total number of the users contained in each communication base station within the time period
Represents the communication base station l at time tiI is more than or equal to 1 and less than or equal to m; the server performs statistical aggregation on the user information collected in a period of time according to a certain time interval, extracts the position information of the communication base station which is most frequently visited by each user in each period of time, and calculates the total number of users in each communication base station in the period of time;
s3, data disturbance stage: time is divided into a day time zone, a night time zone and a late night time zone according to the movement characteristics of a human being, by
Calculating the distribution of the number of people in each base station in each time period
Reference differential privacy mechanism to data in these three time periods
Carrying out different disturbance treatments;
s4, data release stage: the communication operator will process the data
And releasing the message.
Further, the data aggregation stage of step S2 specifically includes the following operation flows:
(1) time period division: dividing according to different time intervals according to the requirement on the resolution of the user moving track, wherein the larger the time interval is, the smaller the resolution of the user moving track is; the smaller the time interval is, the more accurate the user movement track is;
(2) position extraction: after the time interval is divided, a user can have 1 or more access records of different communication base stations in a certain time interval, and at the moment, the base station which is most frequently accessed by the user in the communication base stations is extracted as the position accessed by the user in the time period;
(3) and (3) data statistics: through step (2), it can be known that the user can only access one communication base station under each time stamp, so that each base station (l) under the time stamp t is calculated1,l2,…lm) Number of visits to users in a coverage area
Thereby, the distribution of the number of users in the coverage area of each communication base station in a certain area, namely, the data set under the real-time condition can be obtained
Further, the data perturbation stage of step S3 specifically includes:
(1) in the daytime, the access position of the base station of the user is in a state of continuous updating and changing from 7 am to 6 pm; at this time the data sets D of adjacent time instantst-1And DtThe number of users in the data set D is different, and the data set D is obtained at each timetDirect introduction of Laplace mechanism satisfying differential privacy to add perturbation noise conforming to Laplace distribution
(2) In the evening time period, setting the time from 6 pm to 11 pm, the updating speed of the base station visiting location of the user is reduced; at this time the data sets D of adjacent time instantst-1And DtThe distribution of the number of users still has difference, but the difference is in the case of large or small;
(3) in the late-night time period, from 11 pm to 7 pm, the access location of the base station of the user will not change, and the data set D at the adjacent time ist-1And DtThe user distribution of (2) is almost unchanged; the track privacy of the user can be exposed only in the moving process, and the original data is directly published at the moment.
Further, in order to meet the requirement that the total number n of the base stations does not change, only the first m-1 base stations are subjected to disturbance processing in the step (1), and Noise vectors introduced by the first m-1 base stations are Noisem-1＝(x1,x2,…,xm-1) The noise added by the mth base station is the opposite number according to the noise added by the first m-1 base stations,
further, in the step (2): data set D at adjacent timet-1And DtUnder the condition of large user distribution difference, the position track privacy of the user is threatened, and only the data set D at the current moment needs to be calculatedtAnd the data set D released at the previous momentt-1Comparing the distribution difference with a set fixed threshold value T, and judging whether to carry out disturbance processing on the current data set; thus only a part of the data set D need be addressedtAnd carrying out disturbance processing, and setting the number of the data sets D needing the disturbance processing as C.
Further, the following perturbation method is applied in the evening time period of the step (2), and the perturbation method comprises the following steps:
(1) and (3) privacy budget allocation: before disturbance processing is carried out on the data set D, firstly, the privacy budget is distributed, so that the privacy budget meets the requirement of differential privacy in the whole data disturbance processing stage; make ═ 11+2，1Is used for privacy budgeting in the decision process, an1＝k，2Is a privacy budget used in the perturbation process on the data set D;
(2) a judging stage: in the process, a Laplace mechanism meeting the difference privacy is adopted to add disturbance noise vectors conforming to Laplace distribution
Calculating a noise threshold
And the data set of the current time
And the data set released at the previous moment
Noise value of distribution difference between
(3) A disturbance stage: for the
Introducing a privacy budget of
Adopts a Laplace mechanism satisfying the difference privacy to add the disturbance conforming to the Laplace distributionDynamic noise
Noisem-1＝(x1,x2,…,xm-1),
Computing a noisy data set
Further, in the determination phase of the step (2): when in use
Then pair
Performing perturbation processing, otherwise
Instead of distributing the user's location at the current moment, i.e. publishing
Further, in the perturbation phase of step (3): when the privacy budget is remained, adding the noise of all the remained privacy budgets at the last moment; when privacy budgeting2When exhausted, the subsequent data set will be published with the last distributed data set.
The embodiment also discloses a track privacy protection system of the mobile user based on the differential privacy, which is applied to the server and acts on m communication base stations L ═ L1,l2,…lmN users U ═ U1,u2,…unIn a moving scene, where liIt represents the position of the ith communication base station, i is more than or equal to 1 and less than or equal to m; u. ofjRepresenting the jth user, j is more than or equal to 1 and less than or equal to n, the system comprises the following modules:
an initialization module: when user ujInto a communication base stationiFor recording the relevant information of the user by the server of the communication carrier: the anonymized user ID number, the accessed communication base station position information and the access time t;
a data aggregation module: the server carries out statistical aggregation on the relevant information of the users collected within a period of time according to a certain time interval, extracts the position information of the communication base station with the most frequent access of each user within each time period, and calculates the total number of the users contained in each communication base station within the time period
Represents the communication base station l at time tiI is more than or equal to 1 and less than or equal to m;
a data perturbation module: for dividing time into a day time zone, a night time zone and a late night time zone according to the movement characteristics of human beings, and passing through
Calculating the distribution of the number of people in each base station in each time period
Reference differential privacy mechanism to data in these three time periods
Carrying out different disturbance treatments;
the data release module: for processing data of communication operator
And releasing the message.
For better understanding, as shown in fig. 1: suppose there are 7 users U ═ U1,u2,u3,u4,u5,u6,u7L ═ 3 communication base stations, }, L1,l2,l3}; when each user sends a request service through the base station, the communication base station sends the relevant information of the user to the server and stores the information in the server in a recorded manner; for example, user u1At base station l1When requesting service in the coverage area, the server end stores a record
The server side carries out aggregation statistics according to the collected data records, and at t1In time range, the server discovers the user u1There are 3 access records, respectively
Representing user u1Access a communication base station l1Twice, access the communication base station l2Once, using the base station l with the largest number of accesses1As user u1At t1The location of the base station visited within the time period. Accordingly, the other users are respectively found out at t1Location of base stations visited during a time period, generating a data set
Generating t by the same principle2Data set under time
t3Data set under time
Thereby obtaining a data set
If it is not
For datasets during the daytime, dataset D at each timetDirect introduction of Laplace mechanism satisfying differential privacy to add perturbation noise conforming to Laplace distribution
In order to meet the requirement that the total number of the base stations does not change, only the first 2 base stations are subjected to disturbance treatment, and Noise vectors introduced by the previous base stations are Noise2＝(x1,x2) That is, (1,2), the noise added by the mth base station will be the inverse of the noise added by the first 2 base stations, x3＝-x1-x2＝-3。
If it is not
For a data set at a period of time in the evening, then for a data set at the first time
Introducing Laplace mechanism to carry out disturbance processing and adding noise
Noise2＝(x1,x2)＝(1,0),x3Is-1, available as
For the next time t2Data set of
And judging whether disturbance processing is needed or not. Respectively calculating the noise value of the fixed threshold T, an
And
the noise value of the inter-distance needs to introduce a noise vector generated by a Laplace mechanism
Noise threshold
Noise distance
When in use
Then, the Laplace mechanism of the second layer is added into the noise vector
Can obtain
If it is not
Then
The same method can obtain
If it is not
For a data set in a late-night time period, no perturbation process is performed.
In the above example, during the daytime, direct noise addition is performed directly using laplacian noise satisfying the differential privacy mechanism. And in the evening time period, useThe Laplace mechanism in the two-time difference privacy is adopted, in the Laplace mechanism of the first layer, after disturbance processing is carried out on the fixed threshold T, comparison is carried out to judge whether the Laplace mechanism of the second layer is executed or not, and the current data set D is subjected toiAnd (6) adding noise. The first layer Laplace mechanism satisfies according to Laplace mechanism differential privacy1Differential privacy, second layer Laplace mechanism satisfied2Differential privacy. According to the combination property, the whole mechanism satisfies +1+2The differential privacy of (1) is that deleting the base station access record of any user has no influence on the finally issued data set, so that an attacker cannot recover the movement track of the user according to the issuing result, and the track privacy protection of the mobile user in the process of issuing the aggregated data is realized.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (7)
1. A track privacy protection method of a mobile user based on differential privacy is characterized in that the method is applied to a server and acts on m communication base stations L ═ L1，l2，...lmN users U ═ U1，u2，...unIn a moving scene, where liExpressed as the position of the ith communication base station, i is more than or equal to 1 and less than or equal to m, ujRepresenting the jth user, j is more than or equal to 1 and less than or equal to n, the method comprises the following steps:
s1, initialization stage: when user ujInto a communication base stationiThe server of the communication operator records the relevant information of the user: the anonymized user ID number, the accessed communication base station position information and the access time t;
s2, data aggregation stage: the server carries out statistical aggregation on the relevant information of the users collected in a period of time according to a certain time interval, and extracts the position information of the communication base station with the most frequent access of each user in each time intervalAnd calculating the total number of users in each communication base station at the time interval
Represents the communication base station l at time tiI is more than or equal to 1 and less than or equal to m;
s3, data disturbance stage: time is divided into a day time zone, a night time zone and a late night time zone according to the movement characteristics of a human being, by
Calculating the distribution of the number of people in each base station in each time period
Reference differential privacy mechanism to data in these three time periods
Carrying out different disturbance treatments;
s4, data release stage: the communication operator will process the data
Releasing the product;
the data aggregation stage of step S2 specifically includes the following operation flows:
(1) time period division: dividing according to different time intervals according to the requirement on the resolution of the user moving track, wherein the larger the time interval is, the smaller the resolution of the user moving track is; the smaller the time interval is, the more accurate the user movement track is;
(2) position extraction: after the time interval is divided, a user can have 1 or more access records of different communication base stations in a certain time interval, and at the moment, the base station which is most frequently accessed by the user in the communication base stations is extracted as the position accessed by the user in the time period;
(3) and (3) data statistics: through step (2), it can be known that the user can only access one communication base station under each time stamp, so that each base station (l) under the time stamp t is calculated1，l2，...lm) Number of visits to users in a coverage area
Thereby, the distribution of the number of users in the coverage area of each communication base station in a certain area, namely, the data set under the real-time condition can be obtained
The data perturbation stage of step S3 specifically includes:
(1) in the daytime, the access position of the base station of the user is in a state of continuous updating and changing from 7 am to 6 pm; at this time the data sets D of adjacent time instantst-1And DtThe number of users in the data set D is different, and the data set D is obtained at each timetAdding disturbance noise conforming to Laplace distribution by directly introducing Laplace mechanism satisfying a difference privacy
(2) In the evening time period, setting the time from 6 pm to 11 pm, the updating speed of the base station visiting location of the user is reduced; at this time the data sets D of adjacent time instantst-1And DtThe distribution of the number of users still has difference, but the difference is in the case of large or small;
(3) in the late-night time period, from 11 pm to 7 pm, the access location of the base station of the user will not change, and the data set D at the adjacent time ist-1And DtThe user distribution of (2) is almost unchanged; the track privacy of the user can be exposed only in the moving process, and the original data is directly published at the moment.
2. The privacy-difference-based track privacy protection method for mobile users according to claim 1, wherein in order to ensure that the total number n of base stations does not change, only the first m-1 base stations are disturbed in the step (1), and Noise vectors introduced by the first m-1 base stations are Noisem-1＝(x1，x2，...，xm-1) The noise added by the mth base station is the opposite number according to the noise added by the first m-1 base stations,
3. the differential privacy-based track privacy protection method for mobile users according to claim 1, wherein in the step (2): data set D at adjacent timet-1And DtIn the case of large user distribution difference, only the data set D at the current moment needs to be calculatedtAnd the data set D released at the previous momentt-1Comparing the distribution difference with a set fixed threshold value T, and judging whether to carry out disturbance processing on the current data set; thus only a part of the data set D need be addressedtAnd carrying out disturbance processing, and setting the number of the data sets D needing the disturbance processing as C.
4. The privacy-difference-privacy-based track privacy protection method for mobile users according to claim 1, wherein the following perturbation method is applied in the evening time period of the step (2), and comprises the following steps:
(1) and (3) privacy budget allocation: before disturbance processing is carried out on the data set D, firstly, the privacy budget is distributed, so that the privacy budget meets the requirement of differential privacy in the whole data disturbance processing stage; make ═ 11+2，1Is used for privacy budgeting in the decision process, an1＝k，2Is a privacy budget used in the perturbation process on the data set D;
(2) a judging stage: in the process, it is assumed to be fullLaplace mechanism of sufficient difference privacy to add disturbance noise vector conforming to Laplace distribution
Calculating a noise threshold
And the data set of the current time
And the data set released at the previous moment
Noise value of distribution difference between
(3) A disturbance stage: for the
Introducing a privacy budget of
Adopts a Laplace mechanism satisfying difference privacy to add disturbance noise conforming to Laplace distribution
Noisem-1＝(x1，x2，...，xm-1)，
Computing a noisy data set
5. The differential privacy-based track privacy protection method for mobile users according to claim 4, wherein in the determination phase of step (2): when in use
Then pair
Performing perturbation processing, otherwise
Instead of distributing the user's location at the current moment, i.e. publishing
6. The differential privacy-based track privacy protection method for mobile users according to claim 4, wherein in the perturbation phase of the step (3): when the privacy budget is remained, adding the noise of all the remained privacy budgets at the last moment; when privacy budgeting2When exhausted, the subsequent data set will be published with the last distributed data set.
7. A mobile user trajectory privacy protection system based on score privacy using the method of any one of claims 1 to 6, wherein the system is applied to a server and acts on m communication base stations L ═ { L [ ]1，l2，...lmN users U ═ U1，u2，...unIn a moving scene, where liIt represents the position of the ith communication base station, i is more than or equal to 1 and less than or equal to m; u. ofjRepresenting the jth user, j is more than or equal to 1 and less than or equal to n, the system comprises the following modules:
an initialization module: when user ujInto a communication base stationiFor recording the relevant information of the user by the server of the communication carrier: the anonymized user ID number, the accessed communication base station position information and the access time t;
a data aggregation module: the server carries out statistical aggregation on the relevant information of the users collected within a period of time according to a certain time interval, extracts the position information of the communication base station with the most frequent access of each user within each time period, and calculates the total number of the users contained in each communication base station within the time period
I is more than or equal to 1 and less than or equal to m, and represents the total number of users covered by the communication base station li under the time t;
a data perturbation module: for dividing time into a day time zone, a night time zone and a late night time zone according to the movement characteristics of human beings, and passing through
Calculating the distribution of the number of people in each base station in each time period
Reference differential privacy mechanism to data in these three time periods
Carrying out different disturbance treatments;
the data release module: for processing data of communication operator
And releasing the message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810916399.6A CN109104696B (en) | 2018-08-13 | 2018-08-13 | Track privacy protection method and system for mobile user based on differential privacy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810916399.6A CN109104696B (en) | 2018-08-13 | 2018-08-13 | Track privacy protection method and system for mobile user based on differential privacy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109104696A CN109104696A (en) | 2018-12-28 |
| CN109104696B true CN109104696B (en) | 2020-10-02 |
Family
ID=64849638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810916399.6A Active CN109104696B (en) | 2018-08-13 | 2018-08-13 | Track privacy protection method and system for mobile user based on differential privacy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109104696B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670341A (en) * | 2018-12-29 | 2019-04-23 | 中山大学 | The method for secret protection that a kind of pair of structural data and semi-structured data combine |
| CN110602631B (en) * | 2019-06-11 | 2021-03-05 | 东华大学 | Processing method and processing device for location data for resisting conjecture attack in LBS |
| CN110516476B (en) * | 2019-08-31 | 2022-05-13 | 贵州大学 | Geographical indistinguishable location privacy protection method based on frequent location classification |
| CN112580701B (en) * | 2020-12-09 | 2022-07-12 | 哈尔滨理工大学 | Mean value estimation method and device based on classification transformation disturbance mechanism |
| CN113207120A (en) * | 2021-03-30 | 2021-08-03 | 郑州铁路职业技术学院 | Differential privacy method for collecting user real-time position information in mobile crowd sensing |
| CN115017440B (en) * | 2022-05-31 | 2024-05-07 | 湖南大学 | Aggregation position data release method based on differential privacy protection |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104394509B (en) * | 2014-11-21 | 2018-10-30 | 西安交通大学 | A kind of efficient difference disturbance location intimacy protection system and method |
-
2018
- 2018-08-13 CN CN201810916399.6A patent/CN109104696B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109104696A (en) | 2018-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109104696B (en) | Track privacy protection method and system for mobile user based on differential privacy | |
| Zhang et al. | FASTGNN: A topological information protected federated learning approach for traffic speed forecasting | |
| Cheng et al. | Mobile big data: The fuel for data-driven wireless | |
| Abdulkareem et al. | A review of fog computing and machine learning: concepts, applications, challenges, and open issues | |
| Arain et al. | Location monitoring approach: multiple mix-zones with location privacy protection based on traffic flow over road networks | |
| Zhao et al. | A survey of local differential privacy for securing internet of vehicles | |
| CN103957501B (en) | Long-time request position privacy protection method based on road network prediction | |
| CN110602631B (en) | Processing method and processing device for location data for resisting conjecture attack in LBS | |
| Kim et al. | Deep learning-based privacy-preserving framework for synthetic trajectory generation | |
| Pyrgelis et al. | Privacy-friendly mobility analytics using aggregate location data | |
| Fang et al. | Privatebus: Privacy identification and protection in large-scale bus WiFi systems | |
| WO2020223908A1 (en) | Privacy management | |
| Han et al. | Privacy Protection Algorithm for the Internet of Vehicles Based on Local Differential Privacy and Game Model. | |
| Dawar | Enhancing Wireless Security and Privacy: A 2-Way Identity Authentication Method for 5G Networks | |
| Saravanan et al. | A novel approach of privacy protection of mobile users while using location-based services applications | |
| Al-Dhubhani et al. | A framework for preserving location privacy for continuous queries | |
| Alharthi et al. | Protecting location privacy for crowd workers in spatial crowdsourcing using a novel dummy-based mechanism | |
| He et al. | Cross-screen Tracking Method based on User Behavior Data | |
| CN108111968A (en) | It is a kind of based on extensive location privacy protection method | |
| Swedha et al. | LSTM network for hotspot prediction in traffic density of cellular network | |
| Chen et al. | Differentially private aggregated mobility data publication using moving characteristics | |
| Narayanan et al. | Mining spatial-temporal geomobile data via feature distributional similarity graph | |
| Yan et al. | LDPORR: A localized location privacy protection method based on optimized random response | |
| Errounda | Adaptive Differential Privacy for Decentralized Mobility Data Sharing and Forecasting | |
| Ding et al. | Migration Privacy Protection Based on Scheduling Algorithm for Online Car-Hailing |
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 |