CN115758441A - Method and device for determining private data intersection of multiple parties - Google Patents
Method and device for determining private data intersection of multiple parties Download PDFInfo
- Publication number
- CN115758441A CN115758441A CN202211310010.6A CN202211310010A CN115758441A CN 115758441 A CN115758441 A CN 115758441A CN 202211310010 A CN202211310010 A CN 202211310010A CN 115758441 A CN115758441 A CN 115758441A
- Authority
- CN
- China
- Prior art keywords
- data set
- data
- party
- intersection
- original
- 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
Images
Landscapes
- Storage Device Security (AREA)
Abstract
The embodiment of the specification provides a method and a device for determining a private data intersection of multiple parties, wherein the method comprises the following steps: the method comprises the steps that a first party merges a first obfuscated data set of the party on the basis of a first original data set formed by private data of the party to obtain a first data set; the first party performs joint calculation by using the first data set and a second data set provided by a second party to obtain an overall intersection of the first data set and the second data set; the second data set is obtained by combining a second confusion data set of the second party on the basis of a second original data set formed by private data of the second party; and the first party excludes the data in the total intersection, which belong to the first confusion data set, so that the intersection of the two parties of the first original data set and the second original data set is obtained. The data volumes of the parties can be protected from being revealed in the private data exchange of the determined parties.
Description
Technical Field
One or more embodiments of the present specification relate to the field of computers, and more particularly, to a method and apparatus for determining private data intersection of multiple parties.
Background
At present, in many scenarios, the intersection of private data of multiple parties is determined, and the data of the multiple parties belongs to the private data and cannot be transmitted outside. For example, two parties each hold one dataset, and it is necessary to intersect the two parties without exposing the respective datasets. The intersection can be used for determining matching data of the two parties, so that the two parties can continue to cooperate. Since there is a need to protect private data, it needs to be implemented using secure multiparty computing.
In the prior art, in the process of determining the intersection, private data can be protected from being disclosed, but the data size of each party can be disclosed.
Accordingly, improved schemes are desired to protect the data volumes of parties from leakage in determining private data exchanges for the parties.
Disclosure of Invention
One or more embodiments of the present specification describe a method and apparatus for determining private data intersection of multiple parties, which can protect the data volumes of the parties from leakage in determining private data intersection of multiple parties.
In a first aspect, a method for determining private data intersection of multiple parties is provided, the method comprising:
the method comprises the steps that a first party merges a first obfuscated data set of the party on the basis of a first original data set formed by private data of the party to obtain a first data set;
the first party performs joint calculation by using the first data set and a second data set provided by a second party to obtain an overall intersection of the first data set and the second data set; the second data set is obtained by combining a second confusion data set of the second party on the basis of a second original data set formed by private data of the second party;
and the first party excludes the data in the total intersection, which belong to the first confusion data set, so that the intersection of the two parties of the first original data set and the second original data set is obtained.
In one possible embodiment, the private data is a user identification; after obtaining the intersection of the two parties of the first original data set and the second original data set, the method further includes:
the first party performs longitudinal federal learning with the second party based on the intersection of the two parties.
In one possible embodiment, there is no identical data between the first original data set and the first obfuscated data set;
the first party excluding aliased data in the local set of aliased data in the population intersection, including:
and if the first party determines that the data belonging to the first confusion data set exists in the overall intersection, deleting the data from the overall intersection to obtain the intersection of the two parties.
Further, the first party has private data belonging to a first data space; the data in the first obfuscated data set is obtained by randomly generating data in a first data space.
In one possible embodiment, any data in the first obfuscated data set belongs to the first original data set;
the first party excluding aliased data in the local set of aliased data in the population intersection, including:
and the first party removes repeated data from the overall intersection to obtain the intersection of the two parties.
Further, the data in the first obfuscated data set is obtained by randomly extracting in the first original data set.
In a second aspect, an apparatus for determining an intersection of private data of multiple parties is provided, where the apparatus is provided for a first party, and includes:
the obfuscation unit is used for merging the first obfuscated data set of the local side on the basis of the first original data set formed by the private data of the local side to obtain a first data set;
the combined calculation unit is used for performing combined calculation by using the first data set obtained by the confusion unit and a second data set provided by a second party to obtain a total intersection of the first data set and the second data set; the second data set is obtained by combining a second confusion data set of the second party on the basis of a second original data set formed by private data of the second party;
and the determining unit is used for eliminating data belonging to the first confusion data set in the total intersection obtained by the joint calculation unit to obtain the two-party intersection of the first original data set and the second original data set.
In a third aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of the first aspect.
In a fourth aspect, there is provided a computing device comprising a memory having stored therein executable code and a processor that, when executing the executable code, implements the method of the first aspect.
According to the method and the device provided by the embodiment of the specification, firstly, a first party merges a first obfuscated data set of the party on the basis of a first original data set formed by private data of the party to obtain a first data set; then the first party performs joint calculation by using the first data set and a second data set provided by a second party to obtain the total intersection of the first data set and the second data set; the second data set is obtained by combining a second confusion data set of the second party on the basis of a second original data set formed by private data of the second party; and finally, the first party excludes the data in the total intersection, which belong to the first confusion data set, so that the intersection of the two parties of the first original data set and the second original data set is obtained. As can be seen from the above, in the embodiment of the present specification, the first party does not directly perform joint calculation with the second party by using the original data set of the present party, but introduces obfuscated data on the basis of the original data set, performs joint calculation with the second party by using the first data set to which the obfuscated data is added, and removes the obfuscated data after obtaining the overall intersection, so that leakage of the data size of the original data set is avoided, and the data size of each party can be protected from being leaked in determining the private data intersection of the multiple parties.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram illustrating an implementation scenario of an embodiment disclosed herein;
FIG. 2 illustrates a flow diagram of a method of determining private data intersection of multiple parties, according to one embodiment;
FIG. 3 shows a schematic block diagram of an apparatus that determines private data intersections for multiple parties, according to one embodiment.
Detailed Description
The scheme provided by the specification is described below with reference to the accompanying drawings.
Fig. 1 is a schematic view of an implementation scenario of an embodiment disclosed in this specification. The implementation scenario involves determining an intersection of private data of multiple parties for determining an intersection between a first original data set of private data possessed by a first party and a second original data set of private data possessed by a second party. As shown in fig. 1, a scenario of determining an intersection of private data of multiple parties involves party a and party B, or first and second parties, or party a and party B. The various participants may be implemented as any computing, processing capable device, platform, server, or cluster of devices. Under the condition of protecting data privacy and the data size of each party, the parties jointly determine the intersection of the private data of the parties.
An a party holds a set of n1 private data X = { X1, X2. }, a B party holds a set of n2 private data Y = { Y1, y2.. }, where n1 is the amount of data of the a party and n2 is the amount of data of the B party, and an intersection of X and Y is obtained without exposing the private data and the amount of data in the respective sets, and the intersection can be provided for the a party and/or the B party. For example, a set X = { small bright, small red, small steel }, a set Y = { small bright, small red, small cloud, small blue }, it needs to be determined that the intersection of the two is { small bright, small red }, and the a side cannot know data other than the intersection in the set Y, nor the amount of data in the set Y, and the B side cannot know data other than the intersection in the set X, nor the amount of data in the set X.
In a typical application scenario, the aforementioned party a and party B may correspond to different enterprises, respectively. With the rapid development of the internet, some enterprises accumulate a large amount of data, the enterprises want to be able to use the data to come up on the premise that the enterprises use the data internally, meanwhile, because the internal data sources are generally limited to their own businesses, in order to improve the value of the data, the enterprises also want to combine the data of external enterprises to enhance their own, but when the enterprises share the data, the enterprises do not want to lose ownership of the data, and meanwhile, the data cannot leave their private domains based on compliance requirements, so that a data market based on the privacy computing technology starts to appear, the enterprises release data sets in the data market, while data consumers organize applications on a data privacy computing platform based on the distributed privacy computing technology, and after the applications are organized, the data sets are released to a block chain, and each participant of the joint computing approves and approves or approves the applications, and records the approval results to the block chain, and after each participant passes the approval, the data consumers can execute the distributed computing tasks, and the original computed data are left in their respective private domains, or the computing results are retained for consumption by the private domains or consumer and are recorded in the block chain for review. When each party participating in calculation has larger coincidence in user dimensions, but has less overlapping in characteristic dimensions, longitudinal federated learning is a better choice, and when longitudinal federated learning is performed, the intersection of users of the participating parties is generally required to be obtained first, and then subsequent calculation is performed.
The embodiment of the specification provides a corresponding solution aiming at protecting the data volume of each party from leakage in the privacy data intersection of the plurality of parties.
Fig. 2 shows a flow diagram of a method of determining private data intersection of multiple parties according to one embodiment, which may be based on the implementation scenario shown in fig. 1. As shown in fig. 2, the method for determining the private data intersection of multiple parties in this embodiment includes the following steps: step 21, on the basis of a first original data set formed by private data of a first party, the first party merges a first obfuscated data set of the first party to obtain a first data set; step 22, the first party performs joint calculation by using the first data set and a second data set provided by the second party to obtain an overall intersection of the first data set and the second data set; the second data set is obtained by combining a second confusion data set of the second party on the basis of a second original data set formed by private data of the second party; and 23, the first party excludes the data in the total intersection, which belong to the first confusion data set, to obtain the intersection of the two parties of the first original data set and the second original data set. Specific execution modes of the above steps are described below.
First, in step 21, the first party merges the first obfuscated data set of the own party on the basis of the first original data set composed of private data of the own party to obtain a first data set. It will be appreciated that the first obfuscated data set comprises a number of obfuscated data, wherein the number of obfuscated data comprised by the first obfuscated data set is not known by the second party.
In the embodiments of the present specification, specific meanings represented by the private data are not limited. The privacy data may be, for example, a user identification, attribute information of the user, and the like.
It will be appreciated that the relationship between the data sets of the first party may be expressed as:
{ first data set } = { first raw data set } + { first obfuscated data set }.
There are a number of ways in which the obfuscated data may be generated.
One possible way of generating is such that there is no identical data between the first original data set and the first obfuscated data set. For example, a first party has private data belonging to a first data space; the data in the first obfuscated data set is obtained by randomly generating data in a first data space.
For example, if the first original data set is { a01, a02, a03, a04} and belongs to a first data space of 3 bits composed of letters and numbers, a first obfuscated data set of { B05, F91} can be generated, where the first original data set and the first obfuscated data set do not have the same data, and the merged first data set is { a01, a02, a03, a04, B05, F91}.
Another possible generation is such that any data in the first obfuscated data set belongs to the first original data set. For example, the data in the first obfuscated data set is obtained by randomly drawing in the first original data set. This way of generation can be expressed as:
{ first obfuscated data set } = { first raw data set }. Random%; wherein Random represents a Random number.
For example, if the first original data set is { a01, a02, a03, a04}, a first obfuscated data set may be generated as { a01, a02, a04}, any data in the first obfuscated data set belongs to the first original data set, the merged first data set is { a01, a02, a03, a04, a01, a02, a04}, and duplicate data exists in the first data set.
Then, in step 22, the first party performs joint calculation by using the first data set and a second data set provided by the second party to obtain an overall intersection of the first data set and the second data set; the second data set is obtained by combining a second obfuscated data set of the second party on the basis of a second original data set formed by private data of the second party. It will be appreciated that the second party may derive the second obfuscated data set in a similar manner to the first party.
It will be appreciated that the relationship between the data sets of the second party may be expressed as:
{ second data set } = { second raw data set } + { second obfuscated data set }.
In the embodiment of the present specification, the joint computation may be multi-party secure computation, and a specific computation manner is not limited, for example, a very intuitive method may be used to perform privacy set intersection, that is, a naive hash method. The participating parties A, B use the same hash function H to calculate the hash value of their respective data, and then send the hashed data to each other, and then can find the intersection.
The above total intersection can be expressed as:
{ global intersection } = { first data set } # second data set }.
Finally, in step 23, the first party excludes the data belonging to the first obfuscated data set in the total intersection to obtain the intersection of the two parties of the first original data set and the second original data set. It will be appreciated that the first party is aware of the obfuscated data in the first obfuscated data set, so that data belonging to the first obfuscated data set in the overall intersection can be excluded.
The process of the above exclusion can be expressed as:
{ two-party intersection } = { ensemble intersection } - { first obfuscated data set }.
In one example, there is no identical data between the first original data set and the first obfuscated data set;
the first party excluding aliased data in the local set of aliased data in the population intersection, including:
and if the first party determines that the data belonging to the first confusion data set exists in the overall intersection, deleting the data from the overall intersection to obtain the intersection of the two parties.
In this example, the first party needs to record the first obfuscated data set used in step 21 in order to exclude data belonging to said first obfuscated data set in the overall intersection in step 23, so that an additional intermediate state saving process is required in the calculation process.
In another example, any data in the first obfuscated data set belongs to the first original data set;
the first party excluding aliased data in the local set of aliased data in the population intersection, including:
and the first party removes repeated data from the overall intersection to obtain the intersection of the two parties.
In the example, after the overall intersection is obtained, the repeated data is removed, so that the requirement of saving states among the confused data sets is avoided, and the overall calculation process is simplified. In addition, if the purpose of the deal is to perform longitudinal federal learning later, the de-duplication is usually the step of data preprocessing in the longitudinal federal learning, so that the whole calculation process is simplified.
In one example, the private data is a user identification; after obtaining the intersection of the two parties of the first original data set and the second original data set, the method further includes:
the first party performs longitudinal federal learning with the second party based on the intersection of the two parties.
Federal learning is also known as Federal machine learning, joint learning, and Union learning. The Federal machine learning is a distributed machine learning framework, the traditional machine learning is subjected to customized privacy protection and transformation, and the user privacy and data safety can be effectively protected when data cooperation and combined modeling are carried out among a plurality of organizations on the basis of compliance. The method needs a credible third party to combine the intermediate results, has relatively weak privacy and uncontrollable results, and can obtain model parameters by multiple parties. Generally, in order to ensure the safety of data in federal learning, there are the following ways: a third party is sought that both parties trust, or a trusted execution environment is introduced to replace the trusted third party. On one hand, a credible third party is difficult to obtain, and an additional third party is introduced, so that the processing period of the system is prolonged, the cost is improved, and the user size information is also obtained by the third party; on the other hand, the trusted execution environment can encrypt the computing content, but data needs to be transferred from the internal environment to the trusted execution environment that both parties can access, so by monitoring network traffic there is also a possibility of revealing user quantum information. The embodiment of the specification does not relate to a third party and a trusted execution environment, and the user size is prevented from being revealed by introducing a confusion data set in the process of asking for delivery.
In addition, it should be noted that the embodiments of the present specification are applicable not only to two-party intersection, but also to three-party intersection or intersection with more parties. For example, the intersection between the parties A, B and C can be obtained by the parties A and B intersecting each other, and then the parties A or B intersecting each other by using the intersection of the two parties.
The introduction of the above method flow is introduced by using the first party as the execution subject, and when the intersection of the two parties is actually determined, the second party needs to participate, and the execution process of the second party is similar to that of the first party, which is not described herein again.
According to the method provided by the embodiment of the specification, firstly, a first party merges a first obfuscated data set of the party on the basis of a first original data set formed by private data of the party to obtain a first data set; then the first party performs joint calculation by using the first data set and a second data set provided by a second party to obtain the total intersection of the first data set and the second data set; wherein the second data set is based on a second original data set formed by private data of the second party, combining the second obfuscated data sets of the local parties; and finally, the first party excludes the data in the total intersection, which belong to the first confusion data set, so as to obtain the intersection of the two parties of the first original data set and the second original data set. As can be seen from the above, in the embodiment of the present specification, the first party does not directly perform joint calculation with the second party by using the original data set of the present party, but introduces obfuscated data on the basis of the original data set, performs joint calculation with the second party by using the first data set to which the obfuscated data is added, and removes the obfuscated data after obtaining the overall intersection, so that leakage of the data size of the original data set is avoided, and the data size of each party can be protected from being leaked in determining the private data intersection of the multiple parties.
According to an embodiment of another aspect, an apparatus for determining an intersection of private data of multiple parties is also provided, where the apparatus is provided at a first party and is configured to perform the method shown in fig. 2 provided in an embodiment of the present specification. FIG. 3 shows a schematic block diagram of an apparatus that determines private data intersections for multiple parties, according to one embodiment. As shown in fig. 3, the apparatus 300 includes:
a obfuscating unit 31, configured to merge a first obfuscated data set of the present party on the basis of a first original data set formed by private data of the present party, to obtain a first data set;
a joint calculation unit 32, configured to perform joint calculation using the first data set obtained by the obfuscating unit 31 and a second data set provided by a second party to obtain an overall intersection of the first data set and the second data set; the second data set is obtained by combining a second confusion data set of the second party on the basis of a second original data set formed by private data of the second party;
a determining unit 33, configured to exclude data belonging to the first obfuscated data set in the total intersection obtained by the joint calculating unit 32, so as to obtain a two-party intersection of the first original data set and the second original data set.
Optionally, as an embodiment, the privacy data is a user identifier; the device further comprises:
and a federal learning unit, configured to perform longitudinal federal learning with the second party based on the two-party intersection after the determining unit 33 obtains the two-party intersection of the first original data set and the second original data set.
Optionally, as an embodiment, there is no identical data between the first original data set and the first obfuscated data set;
the determining unit 33 is specifically configured to delete data belonging to the first confusion data set from the population intersection if it is determined that the data exists in the population intersection, so as to obtain the two-party intersection.
Further, the first party has private data belonging to a first data space; the data in the first obfuscated data set is obtained by randomly generating data in a first data space.
Optionally, as an embodiment, any data in the first obfuscated data set belongs to the first original data set;
the determining unit 33 is specifically configured to remove duplicate data from the overall intersection to obtain the intersection of the two parties.
Further, the data in the first obfuscated data set is obtained by randomly extracting in the first original data set.
With the apparatus provided in this specification, first, the obfuscating unit 31 merges the first obfuscated data set of this party on the basis of the first original data set composed of private data of this party, to obtain a first data set; then, the joint calculation unit 32 performs joint calculation by using the first data set and a second data set provided by a second party to obtain an overall intersection of the first data set and the second data set; the second data set is obtained by combining a second confusion data set of the second party on the basis of a second original data set formed by private data of the second party; finally, the determining unit 33 excludes the data belonging to the first aliased data set from the total intersection to obtain the two-party intersection of the first original data set and the second original data set. As can be seen from the above, in the embodiment of the present specification, the first party does not directly perform joint calculation with the second party by using the original data set of the present party, but introduces obfuscated data on the basis of the original data set, performs joint calculation with the second party by using the first data set to which the obfuscated data is added, and removes the obfuscated data after obtaining the overall intersection, so that leakage of the data size of the original data set is avoided, and the data size of each party can be protected from being leaked in determining the private data intersection of the multiple parties.
According to an embodiment of another aspect, there is also provided a computer-readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method described in connection with fig. 2.
According to an embodiment of yet another aspect, there is also provided a computing device comprising a memory having stored therein executable code, and a processor that, when executing the executable code, implements the method described in connection with fig. 2.
Those skilled in the art will recognize that, in one or more of the examples described above, the functions described in this invention may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the present invention should be included in the scope of the present invention.
Claims (14)
1. A method of determining a private data intersection of multiple parties, the method comprising:
the method comprises the steps that a first party merges a first obfuscated data set of the party on the basis of a first original data set formed by private data of the party to obtain a first data set;
the first party performs joint calculation by using the first data set and a second data set provided by a second party to obtain an overall intersection of the first data set and the second data set; the second data set is obtained by combining a second confusion data set of the second party on the basis of a second original data set formed by private data of the second party;
and the first party excludes the data in the total intersection, which belong to the first confusion data set, so that the intersection of the two parties of the first original data set and the second original data set is obtained.
2. The method of claim 1, wherein the private data is a user identification; after obtaining the intersection of the two parties of the first original data set and the second original data set, the method further includes:
the first party performs longitudinal federal learning with the second party based on the intersection of the two parties.
3. The method of claim 1, wherein there is no identical data between the first original data set and the first obfuscated data set;
the first party excluding aliased data in the local set of aliased data in the population intersection, including:
and if the first party determines that the data belonging to the first confusion data set exists in the overall intersection, deleting the data from the overall intersection to obtain the intersection of the two parties.
4. The method of claim 3, wherein the first party has private data belonging to a first data space; the data in the first obfuscated data set is obtained by randomly generating data in a first data space.
5. The method of claim 1, wherein any data in the first obfuscated data set belongs to the first original data set;
the first party excluding aliased data in the local set of aliased data in the population intersection, including:
and the first party removes repeated data from the overall intersection to obtain the intersection of the two parties.
6. The method of claim 5, wherein the data in the first obfuscated data set is obtained by randomly drawing in the first original data set.
7. An apparatus to determine an intersection of private data for multiple parties, the apparatus disposed at a first party, comprising:
the obfuscation unit is used for merging the first obfuscated data set of the local side on the basis of the first original data set formed by the private data of the local side to obtain a first data set;
the combined calculation unit is used for performing combined calculation by using the first data set obtained by the confusion unit and a second data set provided by a second party to obtain a total intersection of the first data set and the second data set; the second data set is obtained by combining a second confusion data set of the second party on the basis of a second original data set formed by private data of the second party;
and the determining unit is used for eliminating data belonging to the first confusion data set in the total intersection obtained by the joint calculation unit to obtain the two-party intersection of the first original data set and the second original data set.
8. The apparatus of claim 7, wherein the private data is a user identification; the device further comprises:
and the federal learning unit is used for performing longitudinal federal learning with the second party based on the two-party intersection after the determining unit obtains the two-party intersection of the first original data set and the second original data set.
9. The apparatus of claim 7, wherein there is no identical data between the first original data set and the first obfuscated data set;
the determining unit is specifically configured to delete data belonging to the first confusion data set from the population intersection to obtain the two-party intersection if it is determined that the data exists in the population intersection.
10. The apparatus of claim 9, wherein the first party has private data belonging to a first data space; the data in the first obfuscated data set is obtained by randomly generating data in a first data space.
11. The apparatus of claim 7, wherein any data in the first obfuscated data set belongs to the first original data set;
the determining unit is specifically configured to remove duplicate data from the total intersection to obtain the intersection of the two parties.
12. The apparatus of claim 11, wherein the data in the first obfuscated data set is obtained by randomly drawing in the first original data set.
13. A computer-readable storage medium, on which a computer program is stored which, when executed in a computer, causes the computer to carry out the method of any one of claims 1-6.
14. A computing device comprising a memory having stored therein executable code and a processor that, when executing the executable code, implements the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211310010.6A CN115758441A (en) | 2022-10-25 | 2022-10-25 | Method and device for determining private data intersection of multiple parties |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211310010.6A CN115758441A (en) | 2022-10-25 | 2022-10-25 | Method and device for determining private data intersection of multiple parties |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115758441A true CN115758441A (en) | 2023-03-07 |
Family
ID=85353132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211310010.6A Pending CN115758441A (en) | 2022-10-25 | 2022-10-25 | Method and device for determining private data intersection of multiple parties |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115758441A (en) |
-
2022
- 2022-10-25 CN CN202211310010.6A patent/CN115758441A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108830601B (en) | Smart city information safe use method and system based on block chain | |
| TWI684108B (en) | Data statistics method and device | |
| KR102149996B1 (en) | System and method for establishing links between identifiers without exposing specific identification information | |
| WO2015080896A1 (en) | Server-aided private set intersection (psi) with data transfer | |
| CN113761563B (en) | Data intersection calculation method and device and electronic equipment | |
| WO2022068358A1 (en) | Encryption method and apparatus for generating keys on basis of attributes of information, and device | |
| CN114239018A (en) | Method and system for determining number of shared data for protecting privacy data | |
| CN114520721A (en) | Multi-party secure computation privacy intersection method, device, equipment and storage medium | |
| Das et al. | A secure softwarized blockchain-based federated health alliance for next generation IoT networks | |
| Jia et al. | Privacy-preserving blockchain-based nonlinear SVM classifier training for social networks | |
| Chaudhary et al. | Designing A Secured Framework for the Steganography Process Using Blockchain and Machine Learning Technology | |
| JP2022549777A (en) | Partition of requests to blockchain transactions | |
| CN115758441A (en) | Method and device for determining private data intersection of multiple parties | |
| CN115225367A (en) | Data processing method, device, computer equipment, storage medium and product | |
| WO2019085656A1 (en) | Data statistics method and apparatus | |
| RU2774815C2 (en) | Method for safe transmission of parts of data describing single object and stored in different databases | |
| US11907392B2 (en) | System and method utilizing function secret sharing with conditional disclosure of secrets | |
| TWI706370B (en) | Data statistics method and device | |
| WO2022109861A1 (en) | Method, apparatus and device for preparing training data for encrypted machine learning | |
| Tang et al. | Privacy-Preserving Multi-Party Directory Services | |
| Sowmiya et al. | Methods and techniques for privacy preserving in blockchain | |
| He et al. | Secure construction and publication of contingency tables from distributed data | |
| Khakre et al. | A BIG DATA AND IT’S SECURITY CHALLENGE IN DIGITAL MEDIA | |
| Feng et al. | LPP-BPSI: A location privacy-preserving scheme using blockchain and Private Set Intersection in spatial crowdsourcing | |
| CN117494014A (en) | Abnormal object processing method and device, electronic equipment and readable storage medium |
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 |