EP4078422A1 - Procédé d'anonymisation d'une base de données et produit programme ordinateur associé - Google Patents
Procédé d'anonymisation d'une base de données et produit programme ordinateur associéInfo
- Publication number
- EP4078422A1 EP4078422A1 EP20824272.7A EP20824272A EP4078422A1 EP 4078422 A1 EP4078422 A1 EP 4078422A1 EP 20824272 A EP20824272 A EP 20824272A EP 4078422 A1 EP4078422 A1 EP 4078422A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- distribution
- anonymized
- anonymization
- individuals
- database
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
- G06F21/6254—Protecting personal data, e.g. for financial or medical purposes by anonymising data, e.g. decorrelating personal data from the owner's identification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0407—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the identity of one or more communicating identities is hidden
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L2209/00—Additional information or applications relating to cryptographic mechanisms or cryptographic arrangements for secret or secure communication H04L9/00
- H04L2209/42—Anonymization, e.g. involving pseudonyms
Definitions
- TITLE Process for anonymizing a database and associated computer program product
- the present invention relates to a method of anonymizing a database respecting differential confidentiality assumptions.
- the present invention also relates to a computer program product comprising software instructions which, when executed by a computer, implement such an anonymization method.
- the database comprises in particular spatio-temporal data relating to a plurality of individuals.
- These spatio-temporal data are, for example, ticketing data comprising times and places of validation of users in a transport network, in particular rail.
- These data are collected, for example, from subscription cards made up of a smart card communicating with a fixed validation terminal, in particular by means of RFID (for “Radio Frequency Identification”) or NFC (for “Radio Frequency Identification”) technologies. 'English Near Field Communication').
- the subject of the invention is a method for anonymizing a database, the database comprising spatio-temporal data relating to a plurality of individuals, the method comprising at least the following steps: - Aggregation of the data in order to define at least one distribution of presence representative of the number of individuals belonging to a category of interest and present at a place of interest during a given time interval;
- the anonymization process comprises one or more of the following characteristics, taken in isolation or in any technically possible combination:
- the method further comprises a step of comparing the presence distribution and the anonymized distribution on the basis of at least one criterion for evaluating the adequacy between the two distributions;
- the comparison step is carried out on the basis of at least two evaluation criteria including at least one absolute evaluation criterion and at least one relative evaluation criterion;
- the method further comprises a step of verifying the anonymization of the anonymized function by calculating the probability of being able to isolate an individual from among the plurality of individuals from the anonymized distribution;
- the method comprises a reiteration of the steps of the method when at least one of the following conditions is met: at least one evaluation criterion is not met and the probability of being able to isolate an individual is greater than a predetermined threshold;
- the method further comprises a step of providing data relating to the anonymized distribution to the plurality of individuals;
- the presence distribution projection step is performed by a discrete Fourier transform or by a discrete cosine transform
- the place of interest is a station of a public transport network
- the category of interest is the socio-professional group of each individual.
- Figure 1 is a schematic representation of an electronic assembly suitable for implementing an anonymization process according to the invention.
- Figure 2 is a flowchart of an anonymization process according to the invention.
- the electronic assembly 10 comprises at least a database 12, a preprocessing module 14, a processing module 16 and a postprocessing module 18
- the database 12 is suitable for storing a plurality of data.
- Each data is spatio-temporal data relating to an individual.
- a spatio-temporal datum is a datum relating to the geographical position of the individual at a given temporal instant.
- the database 12 includes, for example, ticketing data comprising times and places of validation of users in a transport network, in particular rail.
- the database 12 comprises, for example, data comprising times and places of validation of employees or visitors in a building of a company.
- the database 12 is external to the electronic assembly 10.
- the preprocessing module 14 is able to receive data from the database 12, to process said data in order to obtain at least one distribution of data, as will be explained subsequently, and to transmit the or each distribution to the processing module 16.
- the processing module 16 is able to receive the or each distribution from the preprocessing module 14, to process these distributions in order to obtain at least one anonymized distribution, as will also be explained later, and to transmit the or each distribution anonymized to the post-processing module 18.
- the post-processing module 18 is suitable for receiving the or each anonymized distribution from the processing module 16 and for processing these anonymized distributions as will also be explained below, and for transmitting these data to an external database. 20.
- the preprocessing module 14, the processing module 16 and the postprocessing module 18 each take the form of an independent computer further comprising at least one processor and one memory.
- the aforementioned modules are at least partially in the form of programmable logic circuits of FPGA type (standing for “Field-Programmable Gâte Array”) and / or software stored in the memory of the computer and executable. by the processor thereof.
- the preprocessing module 14, the processing module 16 and the postprocessing module 18 alternatively take the form of a single computer.
- the database 12 comprises spatio-temporal data relating to a plurality of individuals collected previously, for example in a transport network.
- the anonymization process comprises an initial step of aggregating 100 data from the database 12.
- the preprocessing module 14 receives the data from the database 12 and processes them in order to define at least one presence distribution.
- Distribution is understood to mean a statistical distribution associating a given event with its frequency of occurrence.
- An example of a distribution gives the number of users who have passed through a certain station every half hour or the number of students who have been in a specific area of the city comprising several stations over a defined time slot.
- the presence distribution is therefore representative of the number of individuals belonging to a category of interest and present at a place of interest during a given time interval.
- the category of interest is advantageously the socio-professional group of each individual.
- the socio-professional group is for example defined by the nomenclature defined in France by the National Institute of Statistics of Economic Studies (INSEE) or in Europe by the European Socioeconomic Classification ("European Socioeconomic Classification" in English) making it possible to classify the different trades. It is thus possible to aggregate individuals by categories such as students, unemployed, managers, workers, etc.
- the category of interest is, for example, the age of individuals.
- the category of interest defines whether the individuals using the transport network are locals or tourists.
- the category of interest defines a geographic area of residence of network users, such as, for example, the department. It is understood that as a variant, no category of interest can be considered, the aggregates then being made over the entire population.
- the place of interest is advantageously a station of a public transport network.
- the place of interest is a district of a city with several stations.
- the place of interest is the front door of a business building.
- the time interval given is advantageously less than 1 hour, in particular less than 30 minutes, in particular less than 15 minutes in order to obtain sufficiently precise information.
- the preprocessing module 14 transmits the presence distribution (s) to the processing module 16.
- the anonymization process comprises a step 110 of projecting the presence distribution in a base of predetermined functions.
- the processing module 16 determines a decomposition of the presence distribution in said base in order to obtain at least one coefficient in said base.
- the projection of the presence distribution is performed by a discrete Fourier transform or by a discrete cosine transform.
- Said coefficients are here equal to the different values of S (k).
- the anonymization process comprises a step 120 of adding digital noise to the or each a coefficient associated with the presence distribution.
- digital noise is meant a modification of a coefficient by a small deviation from the initial value of the coefficient.
- the ratio between the digital noise and the initial value of the coefficient is such that the noisy data respects a differential confidentiality property as defined beforehand by the user.
- the digital noise advantageously has the form of a Gaussian or Laplacian function.
- the processing module 16 thus applies a digital noise to the or to each coefficient in order to obtain at least one noisy coefficient.
- the anonymization method comprises a step of reconstructing 130 an anonymized distribution from the or each noisy coefficient.
- the processing module 16 applies the inverse function associated with the transformation used to calculate the coefficients.
- the values of the anonymized distribution are here equal to the different values of s (n).
- An anonymized distribution is thus obtained, different from the initial presence distribution but where the loss of information between the two distributions is limited.
- the processing module 6 transmits the anonymized distribution to the post-processing module 18.
- the anonymization method comprises an optional step 140 of comparing the presence distribution and the anonymized distribution on the basis of at least one criterion for evaluating the 'adequacy between the two distributions.
- the evaluation criterion is a statistical criterion making it possible to measure the variability of the values between the two distributions.
- Each evaluation criterion is associated with a predetermined threshold value making it possible to determine whether the two distributions are considered to be in adequacy or not, that is to say if the loss of information between the two distributions is considered acceptable.
- This evaluation criterion is for example an absolute evaluation criterion measuring an absolute numerical difference between the distributions such as for example the root mean square difference.
- this evaluation criterion is for example a relative evaluation criterion measuring a deviation relative to the initial value of the data of the initial presence distribution, such as “Mean Average Percentage Error” (MAPE or Absolute Percentage Error). average in French) thresholded.
- MME Mel Average Percentage Error
- the post-processing module 18 performs the comparison from at least two evaluation criteria including at least one absolute evaluation criterion and at least one relative evaluation criterion.
- the method further comprises an optional step 150 of verifying the anonymization of the anonymized function.
- the post-processing module 18 calculates the probability of being able to isolate an individual among the plurality of individuals from the anonymized distribution.
- the post-processing module 18 checks whether the evaluation criteria or criteria are met. The post-processing module 18 further checks whether the probability of being able to isolate an individual is greater than a predetermined threshold.
- the anonymization process then comprises a reiteration 160 of steps 110 to 130 of the process when at least one of the following conditions is met: at least one evaluation criterion is not met; and
- the probability of being able to isolate an individual is greater than a predetermined threshold.
- the adding step 120 is performed with less digital noise in order to obtain an anonymized distribution closer to the initial presence distribution.
- the addition step 120 is performed with greater digital noise in order to obtain an anonymized distribution further from the initial presence distribution and thus to guarantee confidentiality of the individuals. more important.
- the method comprises an optional step of making available 170 data relating to the anonymized distribution to the plurality of individuals.
- the post-processing module 18 sends the anonymized distribution to the external database 20.
- users of the transport network can then have access to various statistics on the use of a station or a train line in order to adapt their journey accordingly.
- the distribution is anonymized, there is no risk to the confidentiality of the personal data of each individual.
- the invention makes it possible to obtain more precise anonymous spatio-temporal data distributions.
- the invention allows by means of the added digital noise to make the distributions anonymous by slightly modifying these distributions while ensuring that the loss of information is acceptable.
- the invention makes it possible to find a good compromise between minimizing the loss of information and the anonymization of distributions.
- the invention allows a more relevant and complete use of data from the database, in particular to manage the transport network, while guaranteeing the confidentiality of its individuals.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| FR1914871A FR3105488B1 (fr) | 2019-12-19 | 2019-12-19 | Procede d'anonymisation d'une base de donnees et produit programme ordinateur associe |
| PCT/EP2020/086673 WO2021122918A1 (fr) | 2019-12-19 | 2020-12-17 | Procédé d'anonymisation d'une base de données et produit programme ordinateur associé |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4078422A1 true EP4078422A1 (fr) | 2022-10-26 |
Family
ID=71452300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP20824272.7A Pending EP4078422A1 (fr) | 2019-12-19 | 2020-12-17 | Procédé d'anonymisation d'une base de données et produit programme ordinateur associé |
Country Status (4)
| Country | Link |
|---|---|
| EP (1) | EP4078422A1 (fr) |
| CN (1) | CN114868125A (fr) |
| FR (1) | FR3105488B1 (fr) |
| WO (1) | WO2021122918A1 (fr) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150033356A1 (en) * | 2012-02-17 | 2015-01-29 | Nec Corporation | Anonymization device, anonymization method and computer readable medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8281121B2 (en) * | 2010-05-13 | 2012-10-02 | Microsoft Corporation | Private aggregation of distributed time-series data |
| US20150286827A1 (en) * | 2012-12-03 | 2015-10-08 | Nadia Fawaz | Method and apparatus for nearly optimal private convolution |
| CN108763947B (zh) * | 2018-01-19 | 2020-07-07 | 北京交通大学 | 时间-空间型的轨迹大数据差分隐私保护方法 |
| US11188678B2 (en) * | 2018-05-09 | 2021-11-30 | Fujitsu Limited | Detection and prevention of privacy violation due to database release |
| CN109104696B (zh) * | 2018-08-13 | 2020-10-02 | 安徽大学 | 一种基于差分隐私的移动用户的轨迹隐私保护方法及系统 |
-
2019
- 2019-12-19 FR FR1914871A patent/FR3105488B1/fr active Active
-
2020
- 2020-12-17 CN CN202080089017.2A patent/CN114868125A/zh active Pending
- 2020-12-17 EP EP20824272.7A patent/EP4078422A1/fr active Pending
- 2020-12-17 WO PCT/EP2020/086673 patent/WO2021122918A1/fr not_active Ceased
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150033356A1 (en) * | 2012-02-17 | 2015-01-29 | Nec Corporation | Anonymization device, anonymization method and computer readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114868125A (zh) | 2022-08-05 |
| FR3105488B1 (fr) | 2021-11-26 |
| WO2021122918A1 (fr) | 2021-06-24 |
| FR3105488A1 (fr) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20250045777A1 (en) | Methods and systems for generating address score information | |
| US10530877B2 (en) | Method and system for cross channel in-car media consumption measurement and analysis using blockchain | |
| US10621677B2 (en) | Method and system for applying dynamic and adaptive testing techniques to a software system to improve selection of predictive models for personalizing user experiences in the software system | |
| US20170178199A1 (en) | Method and system for adaptively providing personalized marketing experiences to potential customers and users of a tax return preparation system | |
| CN109614556B (zh) | 访问路径预测、信息推送方法及装置 | |
| US20150111591A1 (en) | Multifactorial optimization system and method | |
| US20110040691A1 (en) | System and method for verified presence marketplace | |
| US20170039637A1 (en) | Computer-implemented method, a system and computer program products for assessing the credit worthiness of a user | |
| US20130275348A1 (en) | System and methods for generating optimal post times for social networking sites | |
| CN111105221A (zh) | 用于对等网络上的车辆共享的系统和方法 | |
| WO2017116591A1 (fr) | Procédé et système d'utilisation de données temporelles et/ou de données filtrées temporellement dans un système logiciel pour optimiser, améliorer et/ou modifier une génération d'expériences utilisateur personnalisées relatives à des utilisateurs d'un système de préparation de déclaration fiscale | |
| CN112163963A (zh) | 业务推荐方法、装置、计算机设备和存储介质 | |
| Braaksma et al. | ``Re-make/Re-model'': Should big data change the modelling paradigm in official statistics? | |
| US20240334159A1 (en) | Systems and methods for using spatial and temporal analysis to associate data sources with mobile devices | |
| Haenlein | A social network analysis of customer-level revenue distribution | |
| US11030631B1 (en) | Method and system for generating user experience analytics models by unbiasing data samples to improve personalization of user experiences in a tax return preparation system | |
| Jaisingh et al. | Paving the way for intelligent transport systems (its) privacy implications of vehicle infotainment and telematics systems | |
| US11416944B1 (en) | Blockchain-based systems and methods for self-managed peer group insurance | |
| WO2021122918A1 (fr) | Procédé d'anonymisation d'une base de données et produit programme ordinateur associé | |
| FR3048101A1 (fr) | Procede et dispositif d'evaluation de la robustesse d'une anonymisation d'un jeu de donnees | |
| Magdalena Silaen et al. | Exploring the differences in types of commodities and delivery methods among online shoppers during the early stage of the COVID-19 pandemic | |
| EP4118810A1 (fr) | Procédé de détection d'un usage frauduleux ou abusif d'un service de téléphonie fourni par un opérateur de téléphonie | |
| Blanchard et al. | A highly granular temporary migration dataset derived from mobile phone data in Senegal | |
| CN120821913B (zh) | 一种基于云平台的会展商家实时信息推送方法及系统 | |
| CN119316473B (zh) | 信息推送方法、装置、设备、介质和程序产品 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20220617 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| P01 | Opt-out of the competence of the unified patent court (upc) registered |
Effective date: 20230524 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20240822 |
|
| RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: HITACHI RAIL GTS FRANCE SAS |