CN104915608B - A kind of information physical emerging system secret protection type data classification method - Google Patents
A kind of information physical emerging system secret protection type data classification method Download PDFInfo
- Publication number
- CN104915608B CN104915608B CN201510234860.6A CN201510234860A CN104915608B CN 104915608 B CN104915608 B CN 104915608B CN 201510234860 A CN201510234860 A CN 201510234860A CN 104915608 B CN104915608 B CN 104915608B
- Authority
- CN
- China
- Prior art keywords
- information physical
- physical unit
- decision tree
- node vector
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Abstract
The present invention provides a kind of information physical emerging system secret protection type data classification method, solves the problems, such as privacy compromise of information physical emerging system during distributed data digging using stochastic decision tree and thresholding additive homomorphism password.This method is determined the structure of stochastic decision tree by each unit of information physical emerging system first;Then the nodal value of decision tree is calculated, is finally classified to new example with the Stochastic Decision-making forest and thresholding additive homomorphism public key cryptography built up.The present invention accurately establishes grader using distributed random decision tree, in conjunction with thresholding additive homomorphism password, can carry out the data classification in information physical emerging system under the premise of providing the secret protection of high efficient and reliable.
Description
Technical field
The present invention provides a kind of information physical emerging system secret protection type data classification method based on stochastic decision tree,
Distributed random decision tree and thresholding additive homomorphism password are mainly used during information physical emerging system is classified
Efficient and reliable secret protection is provided, information security and the interleaving techniques application field of data mining are belonged to.
Background technology
Information physical emerging system is the multi-dimensional complicated system of a COMPREHENSIVE CALCULATING, network and physical environment, passes through 3C
Organically blending for (Computation, Communication, Control) technology cooperates with depth, realizes heavy construction system
Real-time perception, dynamic control and information service.Information physical emerging system is the system for having independent behaviour of an intelligence, letter
Breath physics emerging system can not only obtain data from environment, carry out data fusion, extract effective information, and according to system
Rule acts on environment by effector, is widely used in artificial intelligence field.
Data mining is a process for being hidden in wherein information by algorithm search from a large amount of data.Data mining
Maximum advantage is that many analyses and solution to the problem a large amount of problem set can be used for.Data mining is wide due to it
Wealthy applicable surface and ever-increasing market demand, is applied to the multiple fields such as traffic, medical treatment, insurance, finance, manufacture,
Through as one of field with fastest developing speed in computer industry.But if the requirement of privacy and safety limits being total to for data
It enjoys, must just use the data digging method of secret protection type.The method efficiency of traditional cryptography is too low, it is difficult to carry out extensive
Analysis, the method for simply obscuring input and output are difficult to provide reliable safety.Present invention combination stochastic decision tree and thresholding add
Method homomorphism cryptographic technique carries out efficient secret protection type data mining.
Classification is a kind of important data analysing method.It first selects and has divided the data of class as training set, in the instruction
Practice the technology that the upper maintenance data of collection excavates classification, establishes disaggregated model;Classification prediction is carried out for the data that do not classify.Initially
Data Mining Classification application be all based on the algorithm constructed on the basis of memory mostly.Data digging method requires tool at present
Have based on external memory to handle the ability of large-scale data set and with expansible ability.
Stochastic decision tree is a kind of construction method of decision tree, is had based on external memory to handle the energy of large-scale data set
Power and with expansible ability.The structure of random tree is built up by completely self-contained training data, and algorithm can be divided into instruction
White silk and classification two parts.Due to the use being randomly assigned during establishing tree, stochastic decision tree is in calculating speed and safety
Energy aspect is better than other models, is suitble to the demand of the present invention.
Homomorphic cryptography is the cryptological technique of the computational complexity theory based on difficult math question.Homomorphic cryptography is to passing through homomorphism
Encrypted data are handled to obtain an output, are with Same Way processing by the result that this output is decrypted
Output that encrypted initial data obtains is the result is that the same.Homomorphic cryptography mainly multiplies including additive homomorphism, multiplicative homomorphic, mixing
Method homomorphism, subtraction homomorphism etc., the present invention mainly carry out secret communication using the property of additive homomorphism password.
Invention content
Technical problem:The object of the present invention is to provide a kind of information physical emerging system secret protection type data classification sides
Method, this method combine distributed random decision tree and thresholding additive homomorphism password during classification, to solve data digging
Privacy Protection in pick.
Technical solution:Information physical emerging system secret protection type data of the present invention based on stochastic decision tree point
Class method, user first build more stochastic decision trees in information physical emerging system, then with thresholding additive homomorphism password encryption
Decision tree forms a global decisions tree with encrypted decision forest, classifies to data.
Information physical emerging system of the present invention is made of several information physical units and a certificates snap-in,
Wherein the information physical unit is used for certificate for independently collecting and handling data, certificates snap-in.
Information physical emerging system secret protection type data classification method based on stochastic decision tree includes the following steps:
The component units of information physical emerging system are divided into multiple information physical units and a card by step 1) user
Book administrative unit, the information physical unit is for independently collecting and handling data, and certificates snap-in is for issuing card
Book;
Step 2) user in advance places sample format in systems, and the sample format includes sample names, attribute-name
Claim and corresponding attribute value;
Step 3) user starts the data that each information physical unit collects training sample;
The each information physical unit of step 4) is randomly generated the structure of a decision tree, and the decision tree is a kind of tree
The grader of type structure, grader are a kind of computer programs, can data be assigned to known class automatically;
The each information physical unit of step 5) shares the decision tree structure of generation, forms a set;
Step 6) indicates to connect for each decision tree structure in set, each information physical unit in a manner of anonymous
By or refusal, if cannot unanimously receive set in any decision tree structure, need to restart from step 4);
Step 7) trains the process of decision tree to be divided into three kinds of situations, institute according to the approach to cooperation of each information physical unit
The approach to cooperation stated refers to sharing mode of each information physical unit to data and decision tree:
(a) each information physical unit both knows about the node vector value of all decision trees
Step a7.1) each information physical unit calculates decision tree node vector value with the data of oneself, and informs all
Information physical unit, the decision tree node vector value are the combinations for the distribution probability being calculated by decision Tree algorithms;
Step a7.2) each information physical unit adds up the node vector value of all decision trees and average, obtain one it is complete
Office decision tree;
(b) the information physical unit for only possessing decision tree knows the node vector value of all decision trees
Step b7.1) each information physical unit node vector value of the data calculating decision tree of oneself, it only informs and gathers around
There is the information physical unit of decision tree;
Step b7.2) the information physical unit that possesses decision tree adds up the node vector value of all decision trees and average, obtains
The decision tree global to one;
(c) all information physical units do not know the node vector value of all decision trees
Step c7.1) each information physical unit node vector value of the data calculating decision tree of oneself;
Classification of the step 8) for a new example, for three kinds of situations in step 7):
Step 8.1a) each information physical unit holds global decisions tree, directly in local classification;
Step 8.1b) need the information physical unit classified to generate a public and private key for thresholding additive homomorphism public key cryptography
It is right, and issue the certificate that oneself is constructed to certificates snap-in application and need to re-start step if certificate request is unsuccessful
8b), the thresholding additive homomorphism public key cryptography is a kind of public key cryptography, only when have reach threshold number unit agree to solution
When close, holding the unit of private key can just decrypt;
Step 8.1b2) application certificate success after, need the information physical unit classified to the information physical for possessing decision tree
Unit sends out classification request;
Step 8.1b3) possess decision tree information physical unit will be in the node vector value certificate of global decisions tree
The information physical unit for needing to classify is passed back to after public key encryption;
Step 8.1b4) need the information physical unit classified to be reached according to the example of the secret value searching classification of loopback
All nodes, and all encrypted node vector values are multiplied;
Step 8.1b5) need the information physical unit classified to handle thresholding decryption, searching classification result;
Step 8.1c) need the information physical unit classified to generate a public and private key for thresholding additive homomorphism public key cryptography
It is right, and the certificate constructed to certificates snap-in application oneself needs to re-start step if certificate request is unsuccessful
8.1c)
Step 8.1c2) application certificate success after, need the information physical unit classified to be sent out to all information physical units
Classification request;
Step 8.1c3) each information physical unit is by the public key encryption in the decision tree node vector value certificate of oneself
It is passed back to the information physical unit for needing to classify afterwards;
Step 8.1c4) need the information physical unit classified to be reached according to the example of the secret value searching classification of loopback
All nodes, and all encrypted node vector values are multiplied;
Step 8.1c5) need the information physical unit classified to handle thresholding decryption, searching classification result.
Advantageous effect:Present invention uses the Stochastic Decision-making tree algorithms of Classification Algorithm in Data mining, and combine thresholding
Additive homomorphism public key cryptography solves tradition and obscures input output method to realize the secret protection in information physical emerging system
Unstability and pure cipher method the problem of cannot efficiently carrying out.Specifically, of the present invention to be based on Stochastic Decision-making
The information physical emerging system secret protection type data classification method of tree has following advantageous effect:
(1) safety that stochastic decision tree is provided in secret protection more may be used than traditional method for obscuring input and output
Lean on, and calculate and communication cost also much smaller than pure cipher method, be adapted to big data demand, and implement also compared with
It is easy.
(2) stochastic decision tree is suitable for distributed data mining, adapts to multi-party shared data or cooperation carries out data digging
The situation of pick has good adaptability to information physical emerging system.
(3) thresholding additive homomorphism password can be very good to ensure that a side cannot individually decrypt, it is also ensured that non-decrypting
In the case of, the integrality of data will not be destroyed to the operation of data.
Description of the drawings
Fig. 1 is the information physical emerging system secret protection type data classification method flow based on stochastic decision tree.
Specific implementation mode
It is for a more detailed description to the present invention below according to attached drawing and example.
The present invention is specifically described according to weather sample data, and weather sample data includes sample names, Property Name
With corresponding attribute value.Wherein attribute includes that rain or shine (corresponding attribute value has sunny, overcast, rainy), temperature are (right
The attribute value answered has hot, mild, cool), humidity (corresponding attribute value has high, normal), wind-force (corresponding attribute value
Have strong, weak), trip situation (corresponding classification has yes, no).
Assuming that just like the weather data of following table:
The component units of information physical emerging system are divided into two information physical units and a card by step 1) user
Book administrative unit, the information physical unit is for independently collecting and handling data, and certificates snap-in is for issuing card
Book;
Step 2) user in advance by sample format place in systems, including sample names, Property Name (rain or shine, temperature,
Humidity, wind-force, trip situation) and corresponding attribute value;
Step 3) user starts the data that each information physical unit collects training sample, and catalogue number(Cat.No.) returns first for 1-7's
Second information physical unit is returned for 8-14's by a information physical unit, catalogue number(Cat.No.);
The each information physical unit of step 4) is randomly generated the structure of a decision tree, and the decision tree is a kind of tree
The grader of type structure, grader are a kind of computer programs, can data be assigned to known class automatically;
The each information physical unit of step 5) shares the decision tree structure of generation, forms a set;
Step 6) indicates to connect for each decision tree structure in set, each information physical unit in a manner of anonymous
By or refusal, if cannot unanimously receive set in any decision tree structure, need to restart from step 4);
Step 7) trains the process of decision tree to be divided into three kinds of situations, institute according to the approach to cooperation of each information physical unit
The approach to cooperation stated refers to sharing mode of each information physical unit to data and decision tree:
(a) each information physical unit both knows about the node vector value of all decision trees.
The each information physical unit of step 7.1) calculates decision tree node vector value with the data of oneself, and informs all letters
Physical unit is ceased, the decision tree node vector value is the combination for the distribution probability being calculated by decision Tree algorithms;
The each information physical unit of step 7.2) adds up the node vector value of all decision trees and average, obtains an overall situation
Decision tree;
(b) the information physical unit for only possessing decision tree knows the node vector value of all decision trees.
The each information physical unit of step 7.1) calculates the node vector value of decision tree with the data of oneself, only informs and possesses
The information physical unit of decision tree;
The information physical unit that step 7.2) possesses decision tree adds up the node vector value of all decision trees and average, obtains
One global decision tree;
(c) all information physical units do not know the node vector value of all decision trees.
The each information physical unit of step 7.1) calculates the node vector value of decision tree with the data of oneself;
Classification of the step 8) for a new example, for three kinds of situations in step 7):
(a) each information physical unit of step 8.1) holds global decisions tree, directly in local classification;
(b) it is that thresholding additive homomorphism public key cryptography generation one is public and private close that step 8.1), which needs the information physical unit classified,
Key pair, and issue the certificate that oneself is constructed to certificates snap-in application and need to re-start step if certificate request is unsuccessful
Rapid 8.1) the thresholding additive homomorphism public key cryptography is a kind of public key cryptography, only when there is the unit for reaching threshold number same
When meaning decryption, holding the unit of private key can just decrypt;
After step 8.2) applies for certificate success, need the information physical unit classified to the information physical list for possessing decision tree
Member sends out classification request;
Step 8.3) possesses the information physical unit of decision tree by the public affairs in the node vector value certificate of global decisions tree
It is passed back to the information physical unit for needing to classify after key encryption;
Step 8.4) needs the institute that the information physical unit classified is reached according to the example of the secret value searching classification of loopback
There is node, and all encrypted node vector values are multiplied;
Step 8.5) needs the information physical unit classified to handle thresholding decryption, searching classification result;
(c) it is that thresholding additive homomorphism public key cryptography generation one is public and private close that step 8.1), which needs the information physical unit classified,
Key pair, and the certificate constructed to certificates snap-in application oneself needs to re-start step if certificate request is unsuccessful
8.1)
After step 8.2) applies for certificate success, the information physical unit classified is needed to be sent out point to all information physical units
Class is asked;
The each information physical unit of step 8.3) will be after the public key encryption in the node vector value certificate of global decisions tree
It is passed back to the information physical unit for needing to classify;
Step 8.4) needs the institute that the information physical unit classified is reached according to the example of the secret value searching classification of loopback
There is node, and all encrypted node vector values are multiplied;
Step 8.5) needs the information physical unit classified to handle thresholding decryption, searching classification result.
Claims (1)
1. a kind of information physical emerging system secret protection type data classification method, it is characterised in that include the following steps:
The component units of information physical emerging system are divided into multiple information physical units and a certificate pipe by step 1) user
Unit is managed, the information physical unit is used for certificate for independently collecting and handling data, certificates snap-in;
Step 2) user in advance by sample format place in systems, the sample format include sample names, Property Name and
Corresponding attribute value;
Step 3) user starts the data that each information physical unit collects training sample;
The each information physical unit of step 4) is randomly generated the structure of a decision tree, and the decision tree is a kind of tree-shaped knot
The grader of structure, grader are a kind of computer programs, can data be assigned to known class automatically;
The each information physical unit of step 5) shares the decision tree structure of generation, forms a set;
Step 6) for each decision tree structure in set, each information physical unit indicate to receive in a manner of anonymous or
Refusal need to restart if cannot unanimously receive any decision tree structure in set from step 4);
For step 7) according to the approach to cooperation of each information physical unit, the process of training decision tree is divided into three kinds of situations, described
Approach to cooperation refers to sharing mode of each information physical unit to data and decision tree:
A. each information physical unit both knows about the node vector value of all decision trees
Step a7.1) each information physical unit calculates decision tree node vector value with the data of oneself, and informs all information
Physical unit, the decision tree node vector value are the combinations for the distribution probability being calculated by decision Tree algorithms;
Step a7.2) each information physical unit adds up the node vector value of all decision trees and average, obtains an overall situation and determine
Plan tree;
B. the information physical unit for only possessing decision tree knows the node vector value of all decision trees
Step b7.1) each information physical unit node vector value of the data calculating decision tree of oneself,
Only inform the information physical unit for possessing decision tree;
Step b7.2) the information physical unit that possesses decision tree adds up the node vector value of all decision trees and average, obtain one
Global decision tree;
C. all information physical units do not know the node vector value of all decision trees
Step c7.1) each information physical unit node vector value of the data calculating decision tree of oneself;
Classification of the step 8) for a new example, for three kinds of situations in step 7):
Step 8.1a) each information physical unit holds global decisions tree, directly in local classification;
Step 8.1b) need the information physical unit classified to generate a public and private key pair for thresholding additive homomorphism public key cryptography,
And issue the certificate that oneself is constructed to certificates snap-in application and re-start step 8.1b if certificate request is unsuccessful),
The thresholding additive homomorphism public key cryptography is a kind of public key cryptography, only when there is the information physical unit for reaching threshold number same
When meaning decryption, holding the information physical unit of private key can just decrypt;
Step 8.1b2) application certificate success after, need the information physical unit classified to the information physical unit for possessing decision tree
Send out classification request;
Step 8.1b3) possess the information physical unit of decision tree by the public key in the node vector value certificate of global decisions tree
The information physical unit for needing to classify is passed back to after encryption;
Step 8.1b4) need the information physical unit classified to be owned according to what the example of the secret value searching classification of loopback reached
Node, and all encrypted node vector values are multiplied;
Step 8.1b5) need the information physical unit classified to handle thresholding decryption, searching classification result;
Step 8.1c) need the information physical unit classified to generate a public and private key pair for thresholding additive homomorphism public key cryptography,
And the certificate constructed to certificates snap-in application oneself needs to re-start step 8.1c if certificate request is unsuccessful);
Step 8.1c2) application certificate success after, need the information physical unit classified to send out classification to all information physical units
Request;
Step 8.1c3) each information physical unit will return after the public key encryption in the decision tree node vector value certificate of oneself
Give the information physical unit for needing to classify;
Step 8.1c4) need the information physical unit classified to be owned according to what the example of the secret value searching classification of loopback reached
Node, and all encrypted node vector values are multiplied;
Step 8.1c5) need the information physical unit classified to handle thresholding decryption, searching classification result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510234860.6A CN104915608B (en) | 2015-05-08 | 2015-05-08 | A kind of information physical emerging system secret protection type data classification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510234860.6A CN104915608B (en) | 2015-05-08 | 2015-05-08 | A kind of information physical emerging system secret protection type data classification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104915608A CN104915608A (en) | 2015-09-16 |
CN104915608B true CN104915608B (en) | 2018-07-27 |
Family
ID=54084668
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510234860.6A Active CN104915608B (en) | 2015-05-08 | 2015-05-08 | A kind of information physical emerging system secret protection type data classification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104915608B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105426534A (en) * | 2015-12-21 | 2016-03-23 | 华为技术有限公司 | Information determination method and device |
CN108183897B (en) * | 2017-12-28 | 2021-01-15 | 南京林业大学 | Safety risk assessment method for information physical fusion system |
CN109194523B (en) * | 2018-10-01 | 2021-07-30 | 西安电子科技大学 | Privacy protection multi-party diagnosis model fusion method and system and cloud server |
CN112819058B (en) * | 2021-01-26 | 2022-06-07 | 武汉理工大学 | Distributed random forest evaluation system and method with privacy protection attribute |
CN114265560A (en) * | 2021-12-24 | 2022-04-01 | 金锐软件技术(杭州)有限公司 | Self-standardization storage system for hundred million-level compliance index service data |
CN114282688B (en) * | 2022-03-02 | 2022-06-03 | 支付宝(杭州)信息技术有限公司 | Two-party decision tree training method and system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101587510A (en) * | 2008-05-23 | 2009-11-25 | 中国科学院上海药物研究所 | Method for predicting compound carcinogenic toxicity based on complex sampling and improvement decision forest algorithm |
CN103886030A (en) * | 2014-03-05 | 2014-06-25 | 南京邮电大学 | Cost-sensitive decision-making tree based physical information fusion system data classification method |
CN104601596A (en) * | 2015-02-05 | 2015-05-06 | 南京邮电大学 | Data privacy protection method in classification data mining system |
-
2015
- 2015-05-08 CN CN201510234860.6A patent/CN104915608B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101587510A (en) * | 2008-05-23 | 2009-11-25 | 中国科学院上海药物研究所 | Method for predicting compound carcinogenic toxicity based on complex sampling and improvement decision forest algorithm |
CN103886030A (en) * | 2014-03-05 | 2014-06-25 | 南京邮电大学 | Cost-sensitive decision-making tree based physical information fusion system data classification method |
CN104601596A (en) * | 2015-02-05 | 2015-05-06 | 南京邮电大学 | Data privacy protection method in classification data mining system |
Non-Patent Citations (3)
Title |
---|
分布式决策树挖掘的隐私保护研究;方炜炜;《计算机科学》;20090430;第36卷(第4期);全文 * |
基于SMC的隐私保护聚类模型;方炜炜;《系统工程与电子技术》;20120731;第34卷(第7期);全文 * |
基于隐私保护的决策树模型;方炜炜;《模式识别与人工智能》;20101231;第23卷(第6期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN104915608A (en) | 2015-09-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104915608B (en) | A kind of information physical emerging system secret protection type data classification method | |
US20190207763A1 (en) | Method of searchable public-key encryption and system and server using the same | |
CN110113203B (en) | Method and equipment for security assessment of encryption model | |
CN106407822B (en) | A kind of keyword, multi-key word can search for encryption method and system | |
Ma et al. | A secure face-verification scheme based on homomorphic encryption and deep neural networks | |
CN113518092B (en) | Set intersection method for realizing multi-party privacy | |
CN106972927A (en) | A kind of encryption method and system for different safety class | |
CN108737115A (en) | A kind of efficient privately owned property set intersection method for solving with secret protection | |
CN102629924A (en) | Private information retrieval method in environment of a plurality of servers | |
CN108092766A (en) | A kind of cipher text searching method for verifying authority and its system | |
KR101158864B1 (en) | Distributed computation method and system based on mapreduce of large amount data | |
Kamakshi et al. | Preserving privacy and sharing the data in distributed environment using cryptographic technique on perturbed data | |
CN109617900A (en) | The method of information data encryption based on Internet of Things in conjunction with block chain technology | |
CN106911712A (en) | A kind of encryption method and system for being applied to distributed system | |
Kumar et al. | A hybrid secure cloud platform maintenance based on improved attribute-based encryption strategies | |
Alia et al. | Cryptography based authentication methods | |
Thapa et al. | Asymmetric social proximity based private matching protocols for online social networks | |
CN115081540A (en) | Data privacy protectable classification method and system based on integrated decision learning | |
Das et al. | A secure softwarized blockchain-based federated health alliance for next generation IoT networks | |
CN112380404B (en) | Data filtering method, device and system | |
CN109992977B (en) | Data anomaly point cleaning method based on safe multi-party computing technology | |
CN116561799A (en) | Multiparty privacy set operation method based on cloud server | |
Sattar et al. | Secured aerial photography using Homomorphic Encryption | |
CN108632257A (en) | Support the acquisition methods and system of the encryption health records of hierarchical search | |
Sathya et al. | Efficient privacy preservation technique for healthcare records using big data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |