CN109409132A - A kind of negative investigation method with personalized privacy protection function - Google Patents
A kind of negative investigation method with personalized privacy protection function Download PDFInfo
- Publication number
- CN109409132A CN109409132A CN201811298290.7A CN201811298290A CN109409132A CN 109409132 A CN109409132 A CN 109409132A CN 201811298290 A CN201811298290 A CN 201811298290A CN 109409132 A CN109409132 A CN 109409132A
- Authority
- CN
- China
- Prior art keywords
- option
- negative
- surveyee
- investigation
- server end
- 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; 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)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Storage Device Security (AREA)
Abstract
The present invention surveyee in negative fact-finding process can not unrestricted choice privacy protected degree aiming at the problem that, propose a kind of negative investigation method with personalized privacy protection function.This method uses that undefined term is negative to be collected, handles data on the basis of conventional negative is investigated, and can allow the accuracy and the protected degree of privacy of user's unrestricted choice information, is effective against network interception and attacks and restore reliable data.The present invention questionnaire survey, location information protection etc. suitable for daily life.
Description
One, technical field
The invention belongs to information security fields, and in particular to a kind of negative investigation side with personalized privacy protection function
Method.
Two, background technique
In traditional investigation method, surveyee needs to select the option to tally with the actual situation according to problem.But, it adjusts
The result for interrogating topic may relate to the privacy information of surveyee, for example take in, health status etc..In recent years, investigation quilt is born
It proposes, to realize the privacy of protection surveyee.In negative investigation, surveyee does not need to select true option (referred to as just
Option), it is only necessary to selection does not meet the option (referred to as negative option) of actual conditions.For example, " your monthly income is more to investigation problem
Few member? " option includes: " A. 3,000 or less;B. 3 thousand to five thousand;C. 5 thousand to one ten thousand;D. 10,000 or more ", surveyee's first
Truth be B, then first is only needed from " A, C, D " randomly choose a submission in negative investigation.Investigator is according to first
Certain content submitted, it is known that the truth of first is its one of three kinds of situation that do not submit, the probability of each case is
1/3.Therefore investigator can not accurately recognize the real information of first, to protect the privacy of first.Negative investigation is simultaneously
Evaluation method is provided for investigator, the negative option that can be submitted according to multiple surveyees more accurately estimates true
In the case of the ratio that is selected of each option.Existing negative investigation method can obtain unbiased estimation result, estimation
Error very little.
However, in real life, the secret protection demand of each surveyee is often different, some surveyees'
Secret protection requires height, the secret protection of some surveyees requires low.For example, surveyee's first, which compares, focuses on privacy guarantor
Shield is only ready to submit a negative option to investigator;And surveyee Person B is of less demanding to secret protection, is ready to submit two
Negative option.Part surveyee submits multiple negative options to be conducive to the precision that investigator improves estimation, however existing negative investigation
Scheme does not consider the different situation of the negative option number that each surveyee submits, can not support each surveyee according to
The personalized secret protection of itself requires to submit the different negative options of number, i.e., cannot support the personalized secret protection of surveyee
Demand.
Three, summary of the invention
1, goal of the invention
The present invention surveyee in negative fact-finding process can not unrestricted choice privacy protected degree aiming at the problem that, provide
A kind of negative investigation method with personalized privacy protection function.When being investigated, surveyee can with unrestricted choice j (1≤
J≤C-2, wherein C is total option number) a negative option submitted, and corresponding j value is bigger, then accuracy of information is higher, privacy
Degree of protection is smaller;Corresponding j value is smaller, then accuracy of information is lower, and secret protection degree is bigger.The value of j depends on being adjusted
The person of looking into protects the specific requirements of oneself privacy, is freely determined by surveyee.
Present invention aim to address in negative fact-finding process, surveyee can not freely weigh the protected degree of privacy
Problem.The present invention provides a kind of negative investigation methods with personalized privacy protection function thus.The method is with respect to forefathers'
Method no longer selects the number of option to make stringent limitation each surveyee, thus can freely adapt to the difference of different crowd
Secret protection demand.
2, technical solution
The purpose of the present invention is achieved through the following technical solutions:
2.1. parameter is arranged
A kind of negative investigation method with personalized privacy protection function, parameter agree as follows:
Assuming that:
N is total number of persons
C is option number.
PiIt is the number that i-th is selected in positive investigation.
λjIt is the probability of j option of each person in negative investigation.
RijIt is to bear to investigate the number for selecting i-th under conditions of selecting j option.
piIt is the ratio for selecting i-th number to account for total number of persons in positive investigation.
It the described method comprises the following steps
2.2. Step 1: collecting data:
There is N number of people to participate in investigation, they are x respectively1, x2, x3..., xN.C option is shared, they are y respectively1, y2,
y3..., yC。
2.2.1. (1) surveyee xk(1≤k≤N) can be from set { y1, Y2, Y3..., yCIn arbitrarily select j (1≤j
≤ C-2) a negative option and its option number of blotter be i1, i2..., ij, submit the data to server.
2.2.2 (2) then update two-dimensional array R [C] [C-2] (two-dimensional array is initially set to complete zero array), specifically do
Method is by R [i1] [j], R [i2] [j] ..., R [ij] [j] value all plus one, whole surveyees form two after submitting
Dimension group Rij。
2.3. Step 2: data processing:
By formulaIt calculatesThe people of i-th (1≤i≤C) item is selected in i.e. positive investigation
Number accounts for the ratio of total number of persons.Wherein RijThe as value of two-dimensional array R [i] [j].
2.4 theoretical proofs:
A kind of negative investigation method correctness proof with personalized privacy protection function is as follows:
It can be seen that
So being obtained by (2) formula
Select several options unrelated since any one surveyee is selected in positive investigation in that option and his negative investigation.
It is obtained by (1) formula
It can calculate
So expression formula can be allotted
To guarantee that influence of the selection of each surveyee to final result is impartial
To which final result is
As can be seen that working as λkWhen=100%, it is that K selectes negative investigation variance (1 < K < C-1) of item which, which degenerates,.
2.5 superiority:
It is investigated relative to conventional negative, has the advantages that the negative investigation method of personalized privacy protection function is: the present invention
The investigation that is negative provides personalized solution, provides free secret protection degree for each surveyee, while ensure that number
According to order of accuarcy, the demand of different crowd can adapt to.
Four, Detailed description of the invention
The invention will be further described with reference to the accompanying drawings and embodiments:
Fig. 1 is a kind of flow chart of the negative investigation method with personalized privacy protection function of the present invention
Five, specific embodiment
Above scheme is described further below in conjunction with specific example.It should be understood that these embodiments are for illustrating this
It invents and is not limited to limit the scope of the invention.Based on the embodiment of the present invention, those of ordinary skill in the art are not making
Every other embodiment obtained, belongs to protection scope of the present invention under the premise of creative work.
The present invention uses written in Java experimental code, the experiment of the negative investigation of simulation undefined term, and by experimental result with it is original
Data compare.The present invention passes through the method simulant-client of random number, and positive option is distributed random generation according to different probability,
Comprising being uniformly distributed, bi-distribution, Poisson distribution, the negative option number selected in undefined term is also distributed according to different probability random
It generates, comprising being uniformly distributed and normal distribution.
This experiment specific implementation step is as follows:
Setting options number is 10, and replicated experimental units are 50 times.The random positive tune for generating specified distribution of experiment every time
Option is looked into, investigation negative for undefined term, the random negative option number for generating specified distribution generates altogether 6 groups of different distributions combinations
Data.Formula obtained by theoretical research calculates the distribution situation for calculating separately each positive option through the invention.Experimental result is such as
Table 1~6:
Table 1 is uniformly distributed true distribution and the estimation profiles versus of the negative investigation option of an equally distributed undefined term
Option | One | Two | Three | Four | Five |
True distribution | 9.98% | 9.96% | 9.99% | 10.04% | 10.00% |
Estimation distribution | 9.95% | 9.82% | 10.35% | 10.28% | 9.72% |
Option | Six | Seven | Eight | Nine | Ten |
True distribution | 10.01% | 10.05% | 9.93% | 9.98% | 10.05% |
Estimation distribution | 9.99% | 9.88% | 9.99% | 9.98% | 10.03% |
Table 2 is uniformly distributed-the true distribution of the negative investigation option of undefined term of normal distribution and estimate profiles versus
Option | One | Two | Three | Four | Five |
True distribution | 9.97% | 10.03% | 10.01% | 10.03% | 10.02% |
Estimation distribution | 9.93% | 10.30% | 9.94% | 10.10% | 9.88% |
Option | Six | Seven | Eight | Nine | Ten |
True distribution | 10.02% | 9.94% | 10.04% | 9.96% | 9.98% |
Estimation distribution | 9.91% | 9.91% | 9.98% | 9.95% | 10.10% |
The true distribution of the negative investigation option of 3 bi-distribution of table-equally distributed undefined term and estimation profiles versus
Option | One | Two | Three | Four | Five |
True distribution | 0.09% | 0.10% | 4.41% | 11.75% | 20.53% |
Estimation distribution | 0.06% | 0.92% | 4.32% | 11.86% | 20.59% |
Option | Six | Seven | Eight | Nine | Ten |
True distribution | 24.62% | 20.50% | 11.72% | 4.40% | 0.99% |
Estimation distribution | 24.30% | 20.63% | 11.65% | 4.60% | 1.07% |
The true distribution of the negative investigation option of 4 bi-distribution of table-normal distribution undefined term and estimation profiles versus
Option | One | Two | Three | Four | Five |
True distribution | 0.10% | 0.98% | 4.42% | 11.75% | 20.52% |
Estimation distribution | 0.28% | 0.98% | 4.34% | 11.74% | 20.61% |
Option | Six | Seven | Eight | Nine | Ten |
True distribution | 24.60% | 20.52% | 11.71% | 4.44% | 0.97% |
Estimation distribution | 24.68% | 20.49% | 11.55% | 4.44% | 0.89% |
The true distribution of the negative investigation option of 5 Poisson distribution of table-equally distributed undefined term and estimation profiles versus
Option | One | Two | Three | Four | Five |
True distribution | 15.71% | 23.68% | 23.52% | 17.66% | 10.63% |
Estimation distribution | 15.57% | 23.64% | 23.30% | 17.47% | 10.44% |
Option | Six | Seven | Eight | Nine | Ten |
True distribution | 5.29% | 2.27% | 0.88% | 0.27% | 0.09% |
Estimation distribution | 5.49% | 2.38% | 1.08% | 0.36% | 0.27% |
The true distribution of the negative investigation option of 6 Poisson distributions of table-normal distribution undefined term and estimation profiles versus
Option | One | Two | Three | Four | Five |
True distribution | 15.77% | 23.62% | 23.58% | 17.67% | 10.54% |
Estimation distribution | 15.78% | 23.72% | 23.68% | 17.71% | 10.62% |
Option | Six | Seven | Eight | Nine | Ten |
True distribution | 5.31% | 2.28% | 0.84% | 0.29% | 0.09% |
Estimation distribution | 5.22% | 2.06% | 0.86% | 0.27% | 0.10% |
As can be seen from the table, the estimated result of the negative investigation of undefined term is very close to positive option original Distribution Value, i.e. undefined term
The result of negative investigation is reliable.
The present invention relates to a kind of negative investigation methods with personalized privacy protection function.This method is investigated in conventional negative
On the basis of use that undefined term is negative to be collected, handle data, can allow the accuracy and privacy of user's unrestricted choice information
Protected degree is effective against network interception and attacks and restore reliable data.Present invention questionnaire suitable for daily life
Investigation, location information protection etc..
Claims (4)
1. a kind of method for secret protection based on negative investigation, for server end in survey population data to the true of surveyee
Real data carries out personalized protection, it is characterised in that the described method comprises the following steps:
(1) server end generates the questionnaire comprising C option and is sent to surveyee;
(2) surveyee submits 1 to C-2 negative option to server end;
(3) server end statistics is selected and selects i-th number R under conditions of j optionij;
(4) server end passes through C, RijWhole positive investigation probability distribution is estimated, conceptual data is obtained.
2. according to the method described in claim 1, it is characterized in that the method specifically executes in accordance with the following steps:
(a) it includes C option (y that server end, which generates,1, y2, y3..., yc) questionnaire and transmission, surveyee receive questionnaire.
(b) surveyee xiIn option set { y1, y2, y3..., ycIn arbitrarily select a negative option of j (1≤j≤C-2) to submit,
Option number is recorded as i by server end1, i2, i3..., ij。
(c) under conditions of selecting j option in select i-th number record be Rij, specific practice is to establish initial value complete zero
Two-dimensional array R [C] [C-2], often there is a surveyee xiSubmit data then by R [i1] [j], R [i2] [j] ..., R [ij][j]
Value all plus 1, all surveyees obtain two-dimensional array R after submittingij。
(d) it is calculated by formula, to select the number of i-th (1≤i≤C-2) item to account for the ratio of total number of persons, i.e., whole positive investigation probability
Distribution, obtains conceptual data.
3. according to the method described in claim 1, it is characterized in that surveyee can arbitrarily select to submit choosing in the method
The number of item.
4. according to the method described in claim 1, it is characterized in that the method is completed using computer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811298290.7A CN109409132A (en) | 2018-10-26 | 2018-10-26 | A kind of negative investigation method with personalized privacy protection function |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811298290.7A CN109409132A (en) | 2018-10-26 | 2018-10-26 | A kind of negative investigation method with personalized privacy protection function |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109409132A true CN109409132A (en) | 2019-03-01 |
Family
ID=65471308
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811298290.7A Pending CN109409132A (en) | 2018-10-26 | 2018-10-26 | A kind of negative investigation method with personalized privacy protection function |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109409132A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112380567A (en) * | 2020-11-27 | 2021-02-19 | 南京航空航天大学 | Investigation method with confidence based on localized differential privacy |
CN116305262A (en) * | 2023-03-07 | 2023-06-23 | 安徽大学 | Social network topology privacy protection method based on negative investigation |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106127541A (en) * | 2016-06-08 | 2016-11-16 | 中国科学技术大学 | A kind of credit assessment method based on negative investigation and system |
CN107145974A (en) * | 2017-04-25 | 2017-09-08 | 武汉理工大学 | A kind of method that negative investigation is implemented and reconstructs correction data |
CN107145539A (en) * | 2017-04-21 | 2017-09-08 | 武汉理工大学 | A kind of method for handling unreasonable data in negative investigation |
-
2018
- 2018-10-26 CN CN201811298290.7A patent/CN109409132A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106127541A (en) * | 2016-06-08 | 2016-11-16 | 中国科学技术大学 | A kind of credit assessment method based on negative investigation and system |
CN107145539A (en) * | 2017-04-21 | 2017-09-08 | 武汉理工大学 | A kind of method for handling unreasonable data in negative investigation |
CN107145974A (en) * | 2017-04-25 | 2017-09-08 | 武汉理工大学 | A kind of method that negative investigation is implemented and reconstructs correction data |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112380567A (en) * | 2020-11-27 | 2021-02-19 | 南京航空航天大学 | Investigation method with confidence based on localized differential privacy |
CN116305262A (en) * | 2023-03-07 | 2023-06-23 | 安徽大学 | Social network topology privacy protection method based on negative investigation |
CN116305262B (en) * | 2023-03-07 | 2023-10-17 | 安徽大学 | Social network topology privacy protection method based on negative investigation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wu | Analysis of parameter selections for fuzzy c-means | |
CN112465626B (en) | Combined risk assessment method based on client classification aggregation and related equipment | |
Chen et al. | Efficient independent component analysis | |
Holt et al. | Post stratification | |
US9032491B2 (en) | Multi-factor authentication enrollment optimization method and apparatus | |
CN106789338B (en) | Method for discovering key people in dynamic large-scale social network | |
Albatineh et al. | MCS: A method for finding the number of clusters | |
CN109409132A (en) | A kind of negative investigation method with personalized privacy protection function | |
Huang et al. | Collaboration in participant-centric federated learning: A game-theoretical perspective | |
CN111694839A (en) | Time series index construction method and device based on big data and computer equipment | |
CN117828377B (en) | Educational perception clustering method and system based on fairness weighting factors | |
CN105677645B (en) | A kind of tables of data comparison method and device | |
Lovaglio et al. | Classification of longitudinal career paths | |
CN109949010A (en) | Hospital's high-level personnel's evaluation system of big data based on Information System Integration | |
CN109657122A (en) | A kind of Academic Teams' important member's recognition methods based on academic big data | |
CN116361759B (en) | Intelligent compliance control method based on quantitative authority guidance | |
CN113537308B (en) | Two-stage k-means clustering processing system and method based on localized differential privacy | |
CN110941663B (en) | Method and device for acquiring association rule of certificate information | |
CN115630398A (en) | Personalized differential privacy protection method, device and system based on small sample data | |
CN111709478B (en) | Fuzzy clustering method and device based on anchor graph | |
Ng et al. | Comparing the regression slopes of independent groups | |
CN104199828B (en) | A kind of community network construction method based on transaction journal data | |
CN109670227B (en) | Method for estimating parameter pairs of simulation mathematical model based on big data | |
WO2021202289A1 (en) | Deterministic sparse-tree based cryptographic proof of liabilities | |
Hess et al. | Some aspects of the probability sampling technique of controlled selection |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190301 |