CN108537055B - Privacy budget allocation and data release method and system for data query privacy protection - Google Patents
Privacy budget allocation and data release method and system for data query privacy protection Download PDFInfo
- Publication number
- CN108537055B CN108537055B CN201810181229.8A CN201810181229A CN108537055B CN 108537055 B CN108537055 B CN 108537055B CN 201810181229 A CN201810181229 A CN 201810181229A CN 108537055 B CN108537055 B CN 108537055B
- Authority
- CN
- China
- Prior art keywords
- privacy
- query
- data
- epsilon
- budget
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F21/6227—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 where protection concerns the structure of data, e.g. records, types, queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Storage Device Security (AREA)
Abstract
The invention discloses a privacy budget allocation and data release method for data inquiry privacy protection, which comprises the following steps: the method comprises the following steps: setting privacy budget parameters: a data administrator gives a privacy budget of the data according to the importance degree of the data and records the privacy budget as epsilon; setting the number of basic inquiry times of the data, and recording as k; step two: calculating privacy budget of each query; step three: obtaining the sensitivity delta f of query according to the query f submitted by the user; then, by combining with the privacy budget epsilon allocated to the query, applying a differential privacy protection algorithm to the query result, and calculating the noise to be added to obtain the query result containing the noise; step four: and returning a query result containing noise according to the query submitted by the user, so that the privacy of the data is protected. The invention not only provides privacy protection in the data release process and resists conspiracy attack, but also ensures the precision of the previous k times of inquiry, and the data availability is not too low due to infinite distribution of privacy budget.
Description
Technical Field
The invention relates to a privacy budget allocation and data release method and a system thereof for data inquiry privacy protection, belonging to the technical field of information security.
Background
The deep and widespread of information technology makes the data acquisition, storage, release and analysis become fast and convenient. The data mining technology can obtain valuable information from various released data, but can also cause leakage of personal information, and differential privacy is used as an effective privacy protection technology to ensure that the personal information is not leaked while the effective data is released.
The differential privacy protection data release can be divided into two types according to different implementation scenes, namely interactive data release and non-interactive data release. In a non-interactive scene, a system applies a differential privacy algorithm to an original data set, publishes a data set with noise at one time, and then a user directly queries the data set with noise; in an interactive scene, a user submits a query to the system, the system operates the original data set according to the query request and returns the result to the user after applying a differential privacy algorithm, and the user cannot see the full view of the data. According to the sequence combination property of differential privacy, in a non-interactive scene, only the differential privacy algorithm is applied to the original data set once, and all the privacy budgets epsilon are directly allocated to the algorithm. In an interactive scenario, a user needs to apply a differential privacy algorithm once every time the user submits a query, and the sum of privacy budgets consumed by all the algorithms is epsilon. The privacy budget epsilon represents the privacy protection level, and the smaller epsilon, the higher the privacy protection level, but at the same time, more noise is introduced, which leads to the reduction of data availability, so how to effectively allocate the privacy budget is a great challenge in the differential privacy interactive scenario.
The data issuing algorithm in the existing interactive scene mainly researches how to answer more queries with a given privacy budget under the condition of meeting certain accuracy, and although the algorithms ensure the availability of data to a certain extent, the algorithms limit the query times of users and cannot realize infinite queries on data sets.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a privacy budget allocation and data release method and system for data query privacy protection, aiming at the defects of the background technology, so that a user can query a database for infinite times while ensuring data privacy, and the data availability of the former k times of query can be ensured.
In order to solve the technical problems, the invention adopts the following technical scheme:
the invention discloses a privacy budget allocation and data release method for data inquiry privacy protection, which comprises the following steps:
the method comprises the following steps: setting privacy budget parameters:
for a database stored in a computer system, a data administrator gives a privacy budget of data according to the importance degree of the data and records the privacy budget as epsilon, wherein epsilon is more than 0 and less than or equal to 1; setting the number of basic query times of the data, and recording as k, wherein k is less than 200;
step two: calculating privacy budget of each query:
according to the privacy budget epsilon and the basic query times k, realizing infinite distribution of the privacy budget epsilon by utilizing a Poisson probability mechanism; for each data query submitted by a user, the result is recorded as fiCalculate its allocated privacy budget, denoted εiThe specific values are:
step three: calculate the noise added to the data:
result f of each data query to useriCalculating the sensitivity Δ fi(ii) a In combination with privacy budget epsilon allocated to the queryiThe method is to carry out privacy protection on the sensitive information, and the method is to add a bit of noise to the real data, certainly has a theoretical basis, namely meets the condition of differential privacy protection, and the differential privacy protection is a published theoretical result, and applies a differential privacy protection algorithm to calculate the noise required to be added to obtain the inquiry result containing the noise;
step four: returning the results of the user query:
and returning a query result containing noise according to the query submitted by the user, so that the privacy of the data is protected.
In the first step, the privacy budget epsilon represents a privacy protection level, the smaller epsilon, the higher the privacy protection level, otherwise, the lower the privacy protection level is, and meanwhile, epsilon also influences the noise size, and the smaller epsilon will introduce larger noise;
the basic query times k represent the ideal query times of the user, and an accurate query result is returned after k times of query; in order to ensure the privacy of data, when the query times exceed k, the system returns a noise query result.
In the second step, the sequence combination property of differential privacy is applied:
differential privacy protection algorithm M1,M2,…,M∞Respectively satisfy epsiloniDifferential privacy, where 1 ≦ i ≦ infinity, algorithm { M for the same dataset D1,M2,…,M∞Provision of a sequence combination of } to
In the second step, the poisson probability mechanism is specifically as follows:
poisson distribution ofAn expected value e (x) ═ λ representing the average incidence of random time per unit time;
to implement an infinite number of queries by a user in an interactive scenario, the system allocates a privacy budget ε to each query submitted by the useriAnd applying a differential privacy protection algorithm Mi,MiSatisfies epsiloniDifferential privacy, 1 ≦ i ≦ infinity, privacy budget and answer to satisfy
If the expected value of the poisson distribution is equal to the number of basic queries of the user, i.e., e (x) ═ k, thenBoth sides are multiplied by epsilon at the same time,i.e. satisfying the above-mentioned infinite allocation of privacy budgets;
the privacy budget allocation calculation method under the poisson mechanism is as follows:
in step three, the sensitivity Δ fiThe calculation method is as follows:
for any function f: D → RdThe sensitivity of the function f is
The data sets D and D' are adjacent data sets, have the same attribute structure, and have at most one record different from each other.
In the third step, noise is generated through Laplace distribution, so that differential privacy protection is realized, and the output result is as follows:whereinI.e., the Laplace noise variance, the amount of noise and the query sensitivity Δ fiProportional to the allocated privacy budget εiIn inverse proportion.
The invention relates to a privacy budget allocation and data release system for data inquiry privacy protection, which comprises:
the differential privacy budget total quantity setting module is used for setting the differential privacy budget total quantity according to the privacy protection requirement degree;
the differential privacy budget sequence generation module is used for calculating the differential privacy budget in each data query and generating a differential privacy budget sequence;
the random noise calculation module is used for calculating random noise by adopting a differential privacy budget sequence according to the inquiry and the inquiry sensitivity submitted by a user;
and the query result returning module is used for calculating the query result containing the noise and returning the query result to the user.
In the data query scene, the inventionThe method and the device can ensure that the issued data does not reveal the personal privacy of the user, and can improve the usability of the data. After the method determines the sizes of a privacy budget epsilon and basic query times k, infinite distribution is carried out on the privacy budget by utilizing a Poisson mechanism to obtain a privacy budget sequence { epsiloniThen give each query f to the useriAllocating a privacy budget εiInfinite queries can be provided and the first k queries are guaranteed to provide relatively accurate query results. The invention not only provides privacy protection in the data release process and resists conspiracy attack, but also ensures the precision of the previous k times of inquiry, and the data availability is not too low due to infinite distribution of privacy budget.
Drawings
FIG. 1 is a flow diagram of a publication mechanism;
FIG. 2 is a flow diagram of a Poisson mechanism allocating a privacy budget;
fig. 3 is a partial tabular view of the statistics of the waitakiere dataset.
Detailed Description
The following describes the embodiments of the present invention in further detail with reference to the accompanying drawings:
aiming at the problem of privacy budget allocation in the data release process under a differential privacy interactive scene, the invention provides a Poisson mechanism capable of realizing infinite allocation of privacy budgets, a user can set basic query times k according to query requirements, the former k queries can obtain more accurate query results, the data availability of the query results is ensured, and meanwhile, when the query times exceed k, the allocated privacy budgets are smaller and smaller, and the purpose of privacy protection is achieved.
As shown in fig. 1 and 2, the present invention includes the following steps:
the method comprises the following steps: system given privacy budget epsilon
The privacy budget epsilon represents the privacy protection level, the smaller epsilon, the higher the privacy protection level, and conversely, the lower the privacy protection level, and meanwhile epsilon also influences the noise magnitude, and the smaller epsilon can introduce larger noise.
Step two: user input of basic query number k
The basic query times k represent the ideal query times of the user, and the system returns a relatively accurate query result to the k queries. Meanwhile, in order to ensure the privacy of data, when the query times exceed k, the system returns a query result with high noise.
Step three: infinite allocation of privacy budgets by a poisson mechanism
Poisson distribution ofThe expected value e (x) ═ λ represents the average occurrence rate of random time per unit time.
To implement an infinite number of queries by a user in an interactive scenario, the system allocates a privacy budget ε to each query submitted by the useriAnd applying a differential privacy protection algorithm Mi,MiSatisfies epsiloniDifferential privacy (1. ltoreq. i. ltoreq. infinity), privacy budget and should be satisfied
If the expected value of the poisson distribution is equal to the number of basic queries of the user, i.e., e (x) ═ k, thenBoth sides are multiplied by epsilon at the same time,meeting an infinite allocation of privacy budgets.
Because P (X) is large when X is near the mean value, when i is more than or equal to 1 and less than or equal to k, namely the first k times of inquiry, the privacy budget is ensuredThe method can ensure that the previous k times of inquiry can be divided into larger privacy budgets to obtain more accurate inquiry results. When i is>k, when the number of user queries exceeds the number of basic queries, in order to prevent data privacy information from being mined due to multiple queries, the accuracy of query results is limited,allocating a smaller privacy budgetTherefore, the privacy budget allocation method under the poisson mechanism is as follows:
step four: laplace mechanism adds random noise to query result
The differential privacy protection is realized by generating a noise disturbance real output result through Laplace distribution, and the output result is as follows:whereinI.e., the Laplace noise variance, the amount of noise and the query sensitivity Δ fiProportional to the allocated privacy budget εiIn inverse proportion.
Step five: returning the noisy results to the user
Referring to fig. 3, the following takes the statistical information of the waitakie data set as an example, and specifically describes the embodiment of the present invention:
waitakere is a semi-synthetic dataset generated from the census grid dataset in 2006, new zealand, with a total of 186,471 population distributed over 1,340 grid areas we counted the population in each rectangle by randomly placing residents into each grid block, then dividing the entire area into 7,725 non-overlapping rectangles (154 x 113m2 in size).
Step one, taking a privacy budget epsilon as 1, and taking a basic query time k as 10;
step two, calculating privacy budget based on a Poisson mechanism:
step three, according to the query submitted by the user, Laplace adds random noise to the query result, and in order to simplify the operation, a query set F is set as a { F | F solving interval [456,459 ]]Total number of people in, i.e., f1=f2=…=fn=…=f,Δf1=Δf2=…=Δfn=…=Δf=1,f1(D)=f2(D)=…=fn(D)=…=f(D)=131。
When the user submits the 1 st query f1When inquiring about the result f1(D) Adding a random noise Thus a noisy query result may be M1(D)=131+3.762=134.762.
When the user submits the 2 nd query f2When inquiring about the result f2(D) Adding a random noise Thus a noisy query result may be M2(D)=131-5.698=125.20。
By analogy with the rest of the query, when the user submits 10 queries, the privacy budget of 0.996 is consumed, and most of the privacy budget is used for the former 10 queries, so that a relatively accurate query result is provided for the former 10 queries.
When the user submits the 11 th query f11At query result f11(D) Random noise added onThe random number ratio that generally follows this distribution is large, so a noisy query result may be M2(D) 131+122.368 is 253.368. Perturbs the true query result to a great extentThe purpose of privacy protection is achieved.
The later queries and so on, the more queries, the smaller the allocated privacy budget.
In summary, the invention provides a privacy budget allocation and data release method for data query privacy protection, which utilizes a poisson mechanism to realize infinite allocation of privacy budgets according to the sequence combination property of differential privacy, and simultaneously ensures the query precision of the previous k times, thereby ensuring both the privacy of data and the data availability of the previous k times of query.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (6)
1. A privacy budget allocation and data release method for data inquiry privacy protection is characterized by comprising the following steps:
the method comprises the following steps: setting privacy budget parameters:
for a database stored in a computer system, a data administrator gives a privacy budget of data according to the importance degree of the data and records the privacy budget as epsilon, wherein epsilon is more than 0 and less than or equal to 1; setting the number of basic query times of the data, and recording as k, wherein k is less than 200;
step two: calculating privacy budget of each query:
according to the privacy budget epsilon and the basic query times k, realizing infinite distribution of the privacy budget epsilon by utilizing a Poisson probability mechanism; for each data query submitted by a user, the result is recorded as fiCalculate its allocated privacy budget, denoted εiThe specific values are:
step three: calculate the noise added to the data:
result f of each data query to useriCalculating the sensitivity Δ fi(ii) a In combination with privacy budget epsilon allocated to the queryiApplying a differential privacy protection algorithm to the query result, and calculating the noise to be added to obtain the query result containing the noise;
step four: returning the results of the user query:
returning a query result containing noise according to the query submitted by the user, so that the privacy of the data is protected;
in the second step, the poisson probability mechanism is specifically as follows:
poisson distribution ofAn expected value e (x) ═ λ representing the average incidence of random time per unit time;
to implement an infinite number of queries by a user in an interactive scenario, the system allocates a privacy budget ε to each query submitted by the useriAnd applying a differential privacy protection algorithm Mi,MiSatisfies epsiloniDifferential privacy, 1 ≦ i ≦ infinity, privacy budget and answer to satisfy
If the expected value of the poisson distribution is equal to the number of basic queries of the user, i.e., e (x) ═ k, thenBoth sides are multiplied by epsilon at the same time,i.e. satisfying the above-mentioned infinite allocation of privacy budgets;
the privacy budget allocation calculation method under the poisson mechanism is as follows:
2. the method for distributing privacy budgets and publishing data query privacy protection according to claim 1, wherein in step one, the privacy budget epsilon represents a privacy protection level, and the smaller epsilon, the higher the privacy protection level is, and conversely, the lower the privacy protection level is, and meanwhile epsilon also affects the noise size, and the smaller epsilon will introduce the larger noise;
the basic query times k represent the ideal query times of the user, and an accurate query result is returned after k times of query; in order to ensure the privacy of data, when the query times exceed k, the system returns a noise query result.
3. The method for distributing privacy budget and data distribution for data query privacy protection according to claim 1, wherein in the second step, the sequence combination property of differential privacy is applied:
4. The method for privacy budget allocation and data distribution for data query privacy protection according to claim 1, wherein the sensitivity Δ f is in step threeiThe calculation method is as follows:
for any function f: D → RdThe sensitivity of the function f is
The data sets D and D' are adjacent data sets, have the same attribute structure, and have at most one record different from each other.
5. The method for privacy budget allocation and data distribution for data query privacy protection according to claim 4, wherein in step three, noise is generated by Laplace distribution to realize differential privacy protection, and the output result is: whereinI.e., the Laplace noise variance, the amount of noise and the query sensitivity Δ fiProportional to the allocated privacy budget εiIn inverse proportion.
6. A privacy budget allocation and data distribution system for data query privacy protection, comprising:
the differential privacy budget total quantity setting module is used for setting the differential privacy budget total quantity according to the privacy protection requirement degree;
for a database stored in a computer system, a data administrator gives a privacy budget of data according to the importance degree of the data and records the privacy budget as epsilon, wherein epsilon is more than 0 and less than or equal to 1; setting the number of basic query times of the data, and recording as k, wherein k is less than 200;
the differential privacy budget sequence generation module is used for calculating the differential privacy budget in each data query and generating a differential privacy budget sequence;
according to the privacy budget epsilon and the basic query times k, realizing infinite distribution of the privacy budget epsilon by utilizing a Poisson probability mechanism; for each data query submitted by a user, the result is recorded as fiCalculate its allocated privacy budget, denoted εiThe specific values are:
the poisson probability mechanism is specifically as follows:
poisson distribution ofAn expected value e (x) ═ λ representing the average incidence of random time per unit time;
to implement an infinite number of queries by a user in an interactive scenario, the system allocates a privacy budget ε to each query submitted by the useriAnd applying a differential privacy protection algorithm Mi,MiSatisfies epsiloniDifferential privacy, 1 ≦ i ≦ infinity, privacy budget and answer to satisfy
If the expected value of the poisson distribution is equal to the number of basic queries of the user, i.e., e (x) ═ k, thenBoth sides are multiplied by epsilon at the same time,i.e. satisfying the above-mentioned infinite allocation of privacy budgets;
the privacy budget allocation calculation method under the poisson mechanism is as follows:
the random noise calculation module is used for calculating random noise by adopting a differential privacy budget sequence according to the inquiry and the inquiry sensitivity submitted by a user;
calculating the sensitivity delta f _ i of each data query result f _ i of the user; applying a differential privacy protection algorithm to the query result by combining with the privacy budget epsilon _ i allocated to the query, and calculating the noise to be added to obtain the query result containing the noise;
the query result returning module is used for calculating the query result containing the noise and returning the query result to the user;
and returning a query result containing noise according to the query submitted by the user, so that the privacy of the data is protected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810181229.8A CN108537055B (en) | 2018-03-06 | 2018-03-06 | Privacy budget allocation and data release method and system for data query privacy protection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810181229.8A CN108537055B (en) | 2018-03-06 | 2018-03-06 | Privacy budget allocation and data release method and system for data query privacy protection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108537055A CN108537055A (en) | 2018-09-14 |
CN108537055B true CN108537055B (en) | 2022-04-05 |
Family
ID=63486777
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810181229.8A Active CN108537055B (en) | 2018-03-06 | 2018-03-06 | Privacy budget allocation and data release method and system for data query privacy protection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108537055B (en) |
Families Citing this family (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170124152A1 (en) | 2015-11-02 | 2017-05-04 | LeapYear Technologies, Inc. | Differentially private processing and database storage |
US11055432B2 (en) | 2018-04-14 | 2021-07-06 | LeapYear Technologies, Inc. | Budget tracking in a differentially private database system |
CN109543442A (en) * | 2018-10-12 | 2019-03-29 | 平安科技(深圳)有限公司 | Data safety processing method, device, computer equipment and storage medium |
CN109492429B (en) * | 2018-10-30 | 2020-10-16 | 华南师范大学 | Privacy protection method for data release |
AU2019407410B2 (en) * | 2018-12-20 | 2022-09-01 | Nippon Telegraph And Telephone Corporation | Analysis query response system, analysis query execution apparatus, analysis query verification apparatus, analysis query response method, and program |
CN109726594B (en) * | 2019-01-09 | 2023-07-18 | 南京航空航天大学 | Novel track data release method based on differential privacy |
CN109918939B (en) * | 2019-01-25 | 2023-08-11 | 东华大学 | HMM-based user query risk assessment and privacy protection method |
US11755769B2 (en) | 2019-02-01 | 2023-09-12 | Snowflake Inc. | Differentially private query budget refunding |
CN109885769A (en) * | 2019-02-22 | 2019-06-14 | 内蒙古大学 | A kind of active recommender system and device based on difference privacy algorithm |
WO2020200306A1 (en) * | 2019-04-04 | 2020-10-08 | 华控清交信息科技(北京)有限公司 | Data query and calculation method and system, and storage medium |
US10642847B1 (en) * | 2019-05-09 | 2020-05-05 | LeapYear Technologies, Inc. | Differentially private budget tracking using Renyi divergence |
CN110727957A (en) * | 2019-10-15 | 2020-01-24 | 电子科技大学 | Differential privacy protection method and system based on sampling |
CN110889141B (en) * | 2019-12-11 | 2022-02-08 | 百度在线网络技术(北京)有限公司 | Data distribution map privacy processing method and device and electronic equipment |
CA3108956C (en) | 2020-02-11 | 2023-09-05 | LeapYear Technologies, Inc. | Adaptive differentially private count |
CN111797428B (en) * | 2020-06-08 | 2024-02-27 | 武汉大学 | Medical self-correlation time sequence data differential privacy release method |
CN112487472B (en) * | 2020-11-09 | 2023-11-17 | 安徽工业大学 | Self-adaptive differential privacy budget allocation method and system based on interactive query |
CN112329047A (en) * | 2020-11-26 | 2021-02-05 | 中国工商银行股份有限公司 | Private data encryption query method and device |
CN112613065B (en) * | 2020-12-02 | 2024-08-20 | 北京明朝万达科技股份有限公司 | Data sharing method and device based on differential privacy protection |
CN112560094A (en) * | 2020-12-18 | 2021-03-26 | 湖南大学 | Dual optimization-based high-availability graph data privacy protection method |
CN112767693A (en) * | 2020-12-31 | 2021-05-07 | 北京明朝万达科技股份有限公司 | Vehicle driving data processing method and device |
CN112989411A (en) * | 2021-03-15 | 2021-06-18 | Oppo广东移动通信有限公司 | Privacy budget calculation method, device, storage medium and terminal |
CN113259931A (en) * | 2021-04-21 | 2021-08-13 | 亿景智联(北京)科技有限公司 | Geographic information safe transmission method and device based on differential privacy |
CN113486402B (en) * | 2021-07-27 | 2024-06-04 | 平安国际智慧城市科技股份有限公司 | Numerical data query method, device, equipment and storage medium |
CN113779633B (en) * | 2021-09-16 | 2024-04-09 | 咪咕文化科技有限公司 | Data processing method, device and equipment |
CN113553363B (en) * | 2021-09-23 | 2021-12-14 | 支付宝(杭州)信息技术有限公司 | Query processing method and device |
CN117910046B (en) * | 2024-03-18 | 2024-06-07 | 国网河南省电力公司经济技术研究院 | Electric power big data release method based on differential privacy protection |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105474166A (en) * | 2013-03-15 | 2016-04-06 | 先进元素科技公司 | Methods and systems for purposeful computing |
CN106570422A (en) * | 2016-11-16 | 2017-04-19 | 南京邮电大学 | Realization method of dynamic distribution of differential privacy noise |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103279499B (en) * | 2013-05-09 | 2016-11-09 | 北京信息科技大学 | Privacy of user guard method in personalized information retrieval |
CN104133903B (en) * | 2014-08-04 | 2017-05-17 | 华中科技大学 | Data indexing method based on privacy protection |
US9665735B2 (en) * | 2015-02-05 | 2017-05-30 | Bank Of America Corporation | Privacy fractal mirroring of transaction data |
WO2018040104A1 (en) * | 2016-09-05 | 2018-03-08 | 华为技术有限公司 | Method and device for sending search requests |
CN106991335B (en) * | 2017-02-20 | 2020-02-07 | 美达科林(南京)医药科技有限公司 | Data publishing method based on differential privacy protection |
CN106778314A (en) * | 2017-03-01 | 2017-05-31 | 全球能源互联网研究院 | A kind of distributed difference method for secret protection based on k means |
CN107526975A (en) * | 2017-08-10 | 2017-12-29 | 中国人民大学 | A kind of method based on difference secret protection decision tree |
-
2018
- 2018-03-06 CN CN201810181229.8A patent/CN108537055B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105474166A (en) * | 2013-03-15 | 2016-04-06 | 先进元素科技公司 | Methods and systems for purposeful computing |
CN106570422A (en) * | 2016-11-16 | 2017-04-19 | 南京邮电大学 | Realization method of dynamic distribution of differential privacy noise |
Non-Patent Citations (1)
Title |
---|
王俊丽等.面向社交网络分析的差分隐私保护研究综述.《高技术通讯》.2015,(第03期), * |
Also Published As
Publication number | Publication date |
---|---|
CN108537055A (en) | 2018-09-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108537055B (en) | Privacy budget allocation and data release method and system for data query privacy protection | |
CN114175568B (en) | Secure multiparty arrival rate and frequency estimation | |
Rogers et al. | LinkedIn's Audience Engagements API: A privacy preserving data analytics system at scale | |
Thomasian | Analysis of fork/join and related queueing systems | |
CN108197492B (en) | Data query method and system based on differential privacy budget allocation | |
CN108776763A (en) | One kind being based on the relevant difference method for secret protection of attribute | |
CN103218305B (en) | The distribution method of memory space | |
TWI706664B (en) | Data storage method and system based on multiple blockchain networks | |
US9361321B1 (en) | Backend capacity report for de-duplicated storage systems | |
CN109669995A (en) | Data storage, quality calculation method, device, storage medium and server | |
L'Ecuyer | Quasi-Monte Carlo methods in finance | |
US10353891B2 (en) | Interpolating conformal input sets based on a target output | |
US10073872B2 (en) | Hybrid heap memory management | |
Fang et al. | Differential privacy with δ-neighbourhood for spatial and dynamic datasets | |
JP2022547433A (en) | Empirical provision of data privacy using noise reduction | |
CN110162395A (en) | A kind of method and device of Memory Allocation | |
EP1492026A2 (en) | System and method for expressing and calculating a relationship between OLAP measures | |
US9213639B2 (en) | Division of numerical values based on summations and memory mapping in computing systems | |
WO2023065477A1 (en) | Spatial text query method and apparatus | |
Yadav et al. | Privacy preserving data mining with abridge time using vertical partition decision tree | |
CN110166279B (en) | Dynamic layout method of unstructured cloud data management system | |
US20040015472A1 (en) | System and method for analytically modeling data organized according to non-referred attributes | |
US20170147393A1 (en) | Cache-efficient system for two-phase processing | |
CN103678562A (en) | Capacity obtaining method and file data allocation method | |
Jia et al. | Database query system with budget option for differential privacy against repeated attacks |
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 |