CN116049877B - Method, system, equipment and storage medium for identifying and desensitizing private data - Google Patents
Method, system, equipment and storage medium for identifying and desensitizing private data Download PDFInfo
- Publication number
- CN116049877B CN116049877B CN202211741149.6A CN202211741149A CN116049877B CN 116049877 B CN116049877 B CN 116049877B CN 202211741149 A CN202211741149 A CN 202211741149A CN 116049877 B CN116049877 B CN 116049877B
- Authority
- CN
- China
- Prior art keywords
- data
- desensitization
- desensitized
- management center
- fusing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000000586 desensitisation Methods 0.000 claims abstract description 54
- 238000013526 transfer learning Methods 0.000 claims abstract description 18
- 230000007246 mechanism Effects 0.000 claims abstract description 16
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 4
- 238000004590 computer program Methods 0.000 claims description 9
- 238000013499 data model Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000013508 migration Methods 0.000 claims description 3
- 230000005012 migration Effects 0.000 claims description 3
- 238000011160 research Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 230000002547 anomalous effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a method for identifying and desensitizing private data, which belongs to the technical field of data security and solves the technical problems of high complexity, high realization cost and large labor consumption in the prior art, and comprises the following steps: recognizing and extracting the privacy data based on the transfer learning technology; desensitizing the extracted privacy data according to a set desensitization strategy to obtain desensitized data; synchronizing desensitized data to a data out-of-domain gateway interface, setting a data fusing threshold, and normally outputting desensitized data conforming to the fusing threshold through the interface; and reporting the desensitized data which does not accord with the fusing threshold value to a management center and realizing a fusing mechanism. The invention also discloses a system, equipment and storage medium for identifying and desensitizing the private data. The invention can identify, monitor and process the sensitive data in various and changeable data transaction privacy data, reduce the risk of leakage of the sensitive data in links such as use, storage and the like, and reduce the security threat caused by the leakage of the sensitive data.
Description
Technical Field
The present invention relates to the field of data security technologies, and in particular, to a method, a system, a device, and a storage medium for identifying and desensitizing private data.
Background
With the wide spread and application of big data in recent years, the value of data resources is gradually valued and accepted, and the demand for data transaction is also increasing.
The data is taken as a novel production element, is a digital, networked and intelligent basis, is rapidly integrated into various links such as production, distribution, circulation, consumption, social service management and the like, deeply changes the production mode, the life style and the social management mode, and has increasingly outstanding effects on improving the production efficiency, the life quality and the innovative social management.
The data transaction market in China is rapidly rising, and timely discovery and management of private information become a problem to be solved currently. The data element circulation market is numerous, how to automatically find private data from massive transaction data is the first problem facing at present, and how to conduct platform information of data compliance desensitization examination from private data content is the second problem. The trust and compliance problems of data transaction in the economy of the data elements are solved, and the trust and compliance problems become one of the most core of a data circulation system.
At present, privacy information identification rules and desensitization of a data transaction platform are mainly collected manually, so that labor and time cost are wasted, and an automatic information discovery, extraction and desensitization method is urgent.
In recent years, the rapid development of artificial intelligence technology has not been advanced in the field of natural language processing, wherein text classification is used for text with different characteristics, and named entity recognition technology is mainly used for information extraction and text data structuring.
The named entity recognition method in the prior art is mainly an entity recognition method based on traditional machine learning and an entity recognition method based on deep learning. An entity identification method based on traditional machine learning, such as an invention patent application document CN111274804A, carries out model learning on marked data through statistics, sends the data to be predicted to model prediction, and calculates the entity with the maximum possibility by using a Viterbi algorithm. A named entity recognition method based on deep learning, such as the application document of patent CN111126068A, constructs a neural network model to learn semantic features and can learn more complicated semantics, but a large amount of labeling data is needed for learning, and the data labeling work is extremely time-consuming and labor-consuming.
Disclosure of Invention
The invention aims to solve the technical problems in the prior art, and aims to provide a method for identifying and desensitizing privacy data, which has the characteristics of high efficiency and real-time performance, and is used for identifying, monitoring and processing sensitive data in various and changeable data transaction privacy data, so that the risk of leakage of the sensitive data in links such as use, storage and the like is reduced, and the security threat caused by the leakage of the sensitive data is reduced.
It is a second object of the present invention to provide a system for private data identification and desensitization.
The third object of the present invention is to provide a computer device.
It is a fourth object of the present invention to provide a computer readable storage medium.
To achieve the above object, the present invention provides a method for identifying and desensitizing private data, comprising the steps of:
s1, identifying and extracting privacy data based on a transfer learning technology;
s2, desensitizing the extracted privacy data according to a set desensitizing strategy to obtain desensitized data;
S3, synchronizing the desensitized data to a data out-of-domain gateway interface, setting a data fusing threshold, and normally outputting the desensitized data conforming to the fusing threshold through the interface; and reporting the desensitized data which does not accord with the fusing threshold value to a management center and realizing a fusing mechanism.
As a further improvement, in step S1, multi-dimensional research and judgment is performed according to the key information extracted by the characteristic of the private data, so as to perform classification and named entity recognition operations.
Further, based on the feature representation and the transfer learning of the relation knowledge fusion, the knowledge is encoded in the form of features and is transmitted to the target field from the source field, so that the task effect of the target field is improved.
Further, knowledge migration between related fields, namely, assuming that the relationship between data in the source field and the target field is the same, adding data in different fields, and transmitting the extracted knowledge backwards to generate virtual data for the category which is invisible in the feature space; enhancing the generalization capability of the semantic mapping function by adding data;
The classification and information sampling of the data transaction are automatically completed in the whole process of transfer learning through feature representation and relationship knowledge fusion, and the classified data transaction sample privacy data can be gradually corrected and enriched.
Further, in step S2, the sensitive data identification rule is parsed, and the data desensitization is performed on the full sensitive data and returned, including the following steps:
S21, acquiring a desensitization data strategy for improving transfer learning, and then acquiring a data source type;
S22, analyzing a sensitive data identification and desensitization strategy, and binding a sample data source to identify and desensitize the sensitive data to obtain desensitized data;
s23, analyzing a preview instruction of the management center, and sending a desensitized data source to the management center;
S24, aiming at formatted data, carrying out asymmetric encryption on the whole field, burying a related decryption key in a new field of a data source, and applying a certificate issued by a user and the data source decryption key to a management center to obtain a whole decryption mode if the data source is required to be decrypted later;
s25, encrypting the field aiming at the non-formatted data;
and S26, establishing connection with a management center, and reporting the desensitized progress information of the file in real time.
Further, in step S3, the traffic of the outgoing domain is monitored by using the timing model and the firewall device; downloading the desensitized data source through the data downloading server information of the data downloading rule; the method comprises the following steps:
s31, acquiring a domain-out access rule of desensitization data of a management center, and synchronously outputting the desensitization data through an interface;
s32, establishing a related time sequence data model according to a data flow interface of the desensitization data in a period of time;
s33, acquiring an internal firewall mechanism of a management center, and setting a data fusing threshold for preventing malicious recognition;
And S34, the desensitization data is normally output through the interface according with the setting of the fusing threshold value, is not met, and is reported to the management center and the fusing mechanism is realized.
Further, the time sequence data model is:
Where v represents the text content in the website, and p (c 1 |v) represents the probability of whether the text belongs to or not, and is obtained by the time sequence data and the firewall. g (c 1, v) is used to determine whether the data out-of-domain gateway v belongs to the anomalous data class c 1. If g (c 1, v) is not less than 0, it indicates that v belongs to abnormal data c 1 in a certain period of time.
To achieve the second object, the present invention provides a system for identifying and desensitizing private data, comprising:
The identification module is used for identifying and extracting the privacy data based on the transfer learning technology;
The desensitization module is used for carrying out desensitization processing on the extracted privacy data according to a set desensitization strategy to obtain desensitized data;
the output module synchronizes the desensitized data to the data out-of-domain gateway interface, sets a data fusing threshold value, and normally outputs the desensitized data conforming to the fusing threshold value through the interface; and reporting the desensitized data which does not accord with the fusing threshold value to a management center and realizing a fusing mechanism.
In order to achieve the third object, the present invention provides a computer device, including a memory and a processor, the memory storing a computer program, the processor implementing a method of privacy data identification and desensitization as described above when executing the computer program.
In order to achieve the above object, the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of privacy data identification and desensitization as described above.
Advantageous effects
Compared with the prior art, the invention has the advantages that:
The invention uses a transfer learning mode to classify and extract privacy information, and automatically uses an asymmetric encryption mode to encrypt data and automatically and safely distribute the desensitized sensitive key information; the invention can automatically complete the classification and information sampling of the privacy data in the data transaction in the whole course, and can gradually correct and enrich the identification of the privacy data of the classified data transaction, thereby achieving continuous evolution and improvement.
Drawings
FIG. 1 is a schematic diagram of the present invention;
Fig. 2 is a flow chart of a business.
Detailed Description
The invention will be further described with reference to specific embodiments in the drawings.
Referring to fig. 1-2, a method for identifying and desensitizing private data includes the steps of:
S1, privacy data are identified and extracted based on a transfer learning technology. According to the key information extracted by the characteristic of the privacy data, the characteristic such as important data such as personal name, mobile phone number, identity card, longitude and latitude, and the related characteristic of personal data, the extracted key information is utilized to carry out multidimensional research and judgment so as to carry out classification and named entity recognition operation, such as classification and named entity recognition operation on texts, text pictures and formatted data.
1) Based on the transfer learning of feature representation and relation knowledge fusion, the knowledge is encoded in the form of features and is transmitted to the target field from the source field, so that the task effect of the target field is improved.
2) Knowledge migration between related fields, namely, supposing that the relationship between data in source fields and target fields is the same, adding data in different fields, and transmitting the extracted knowledge backwards to generate virtual data for categories which are invisible in a feature space; the generalization ability of the semantic mapping function is enhanced by adding data.
The classification and information sampling of the data transaction are automatically completed in the whole process of transfer learning through feature representation and relationship knowledge fusion, and the classified data transaction sample privacy data can be gradually corrected and enriched.
The improved transfer learning model is used for analyzing the sensitive data identification rule, scanning the data sources in batches, determining the type of the sensitive data file to identify the sensitive data of the data source content, and recording identification log information.
The input is the policy module parsing the sensitive data recognition policy result and is input to the sensitive data recognition algorithm engine.
1) And acquiring and analyzing a data acquisition rule configuration strategy of the management center, and then acquiring a data source.
2) And acquiring and analyzing a sensitive data identification strategy of the management center, and then carrying out sensitive data identification on the data source.
3) And generating a sensitive data identification log according to the identification result and uploading the sensitive data identification log to a management center.
And S2, performing desensitization treatment on the extracted privacy data according to a set desensitization strategy to obtain desensitized data. Analyzing the sensitive data identification rule, performing data desensitization on the full sensitive data and returning, wherein the method comprises the following steps of:
S21, acquiring a desensitization data strategy for improving transfer learning, and then acquiring a data source type;
S22, analyzing a sensitive data identification and desensitization strategy, and binding a sample data source to identify and desensitize the sensitive data to obtain desensitized data;
s23, analyzing a preview instruction of the management center, and sending a desensitized data source to the management center;
S24, aiming at formatted data, carrying out asymmetric encryption on the whole field, burying a related decryption key in a new field of a data source, and applying a certificate issued by a user and the data source decryption key to a management center to obtain a whole decryption mode if the data source is required to be decrypted later;
s25, encrypting the field aiming at the non-formatted data;
and S26, establishing connection with a management center, and reporting the desensitized progress information of the file in real time.
S3, synchronizing the desensitized data to a data out-of-domain gateway interface, setting a data fusing threshold, and normally outputting the desensitized data conforming to the fusing threshold through the interface; and reporting the desensitized data which does not accord with the fusing threshold value to a management center and realizing a fusing mechanism. Monitoring the traffic of the outgoing domain by using a time sequence model and a firewall device; downloading the desensitized data source through the data downloading server information of the data downloading rule; the method comprises the following steps:
s31, acquiring a domain-out access rule of desensitization data of a management center, and synchronously outputting the desensitization data through an interface;
s32, establishing a related time sequence data model according to a data flow interface of the desensitization data in a period of time;
s33, acquiring an internal firewall mechanism of a management center, and setting a data fusing threshold for preventing malicious recognition;
And S34, the desensitization data is normally output through the interface according with the setting of the fusing threshold value, is not met, and is reported to the management center and the fusing mechanism is realized.
The time sequence data model is as follows:
Where v represents the text content in the website, and p (c 1 |v) represents the probability of whether the text belongs to or not, and is obtained by the time sequence data and the firewall. g (c 1, v) is used to determine whether the data out-of-domain gateway v belongs to the anomalous data class c 1. If g (c 1, v) is not less than 0, it indicates that v belongs to abnormal data c 1 in a certain period of time.
Several kinds of policy information are described below:
1) Device information, user information, and user rights authorization mechanisms.
2) And the sensitive data analysis model is used for classifying sensitive data and initializing data extraction.
3) And the analysis management center acquires remote data source strategy configuration information field sampling analysis, such as finding sensitive data, and issuing analysis.
5) And analyzing the sensitive data identification strategy, and analyzing the sensitive data identification strategy configuration information field of the analysis management center.
6) And resolving the sensitive data desensitization strategy, and resolving the sensitive data desensitization strategy configuration information field of the resolving management center.
7) And (3) generating a sensitive data report, which is responsible for analyzing sensitive data statistics in the gateway and generating the report.
The policy synchronization requires that the static desensitization gateway monitor the full synchronization of each policy information of the management center in real time.
In order to realize the display of the running state of the real-time gateway, the timely warning of faults and the review of the historical state, a time sequence characteristic model and a monitoring and warning system of a related firewall are constructed, unified analysis and warning of logs and safety events of the whole network safety equipment are realized, the discovery, detection and warning of advanced threats and unknown threats are realized, and a safety event report is provided. And detecting and blocking the abnormal network data packet information and alarming, thereby achieving the gateway device for safe distribution.
A system for private data identification and desensitization, comprising:
The identification module is used for identifying and extracting the privacy data based on the transfer learning technology;
The desensitization module is used for carrying out desensitization processing on the extracted privacy data according to a set desensitization strategy to obtain desensitized data;
the output module synchronizes the desensitized data to the data out-of-domain gateway interface, sets a data fusing threshold value, and normally outputs the desensitized data conforming to the fusing threshold value through the interface; and reporting the desensitized data which does not accord with the fusing threshold value to a management center and realizing a fusing mechanism.
A computer device comprising a memory storing a computer program and a processor implementing a method of privacy data identification and desensitisation as described above when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of privacy data identification and desensitization as described above.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present invention, and these do not affect the effect of the implementation of the present invention and the utility of the patent.
Claims (6)
1. A method of private data identification and desensitization comprising the steps of:
s1, identifying and extracting privacy data based on a transfer learning technology;
s2, desensitizing the extracted privacy data according to a set desensitizing strategy to obtain desensitized data;
s3, synchronizing the desensitized data to a data out-of-domain gateway interface, setting a data fusing threshold, and normally outputting the desensitized data conforming to the fusing threshold through the interface; the desensitized data which does not accord with the fusing threshold value is reported to the management center and a fusing mechanism is realized;
in step S1, multi-dimensional research and judgment are performed according to the key information extracted by the characteristic of the private data, so as to perform classification and named entity recognition operations;
in step S2, analyzing the sensitive data identification rule, performing data desensitization on the full sensitive data, and returning, including the following steps:
S21, acquiring a desensitization data strategy for improving transfer learning, and then acquiring a data source type;
S22, analyzing a sensitive data identification and desensitization strategy, and binding a sample data source to identify and desensitize the sensitive data to obtain desensitized data;
s23, analyzing a preview instruction of the management center, and sending a desensitized data source to the management center;
S24, aiming at formatted data, carrying out asymmetric encryption on the whole field, burying a related decryption key in a new field of a data source, and applying a certificate issued by a user and the data source decryption key to a management center to obtain a whole decryption mode if the data source is required to be decrypted later;
s25, encrypting the field aiming at the non-formatted data;
s26, establishing connection with a management center, and reporting the desensitized progress information of the file in real time;
in step S3, monitoring the traffic of the outgoing domain by using the timing model and the firewall device; downloading the desensitized data source through the data downloading server information of the data downloading rule; the method comprises the following steps:
s31, acquiring a domain-out access rule of desensitization data of a management center, and synchronously outputting the desensitization data through an interface;
s32, establishing a related time sequence data model according to a data flow interface of the desensitization data in a period of time;
s33, acquiring an internal firewall mechanism of a management center, and setting a data fusing threshold for preventing malicious recognition;
s34, the desensitization data is normally output through an interface according with the setting of the fusing threshold value, is not met, and is reported to a management center and a fusing mechanism is realized;
The time sequence data model is as follows:
In the above Representing text content in a website,/>Representing the probability of whether the text belongs to, and obtaining the text by time sequence data and a firewall/>For determining data out-of-domain gateway/>Whether or not it belongs to the abnormal data class/>If/>Indicating/>, within a certain period of timeBelonging to abnormal data/>。
2. The method for identifying and desensitizing private data according to claim 1, wherein knowledge is encoded in a form of features based on feature representation and transfer learning of relational knowledge fusion, and is transferred from a source domain to a target domain, so that task effects of the target domain are improved.
3. A method of private data identification and desensitization according to claim 2, wherein knowledge migration between related domains, assuming that the relationship between data is the same in source domain and target domain, adding data in different domains, and the extracted knowledge is transmitted backwards to generate virtual data for classes not visible in feature space; enhancing the generalization capability of the semantic mapping function by adding data;
The classification and information sampling of the data transaction are automatically completed in the whole process of transfer learning through feature representation and relationship knowledge fusion, and the classified data transaction sample privacy data can be gradually corrected and enriched.
4. A system for private data identification and desensitization comprising:
The identification module is used for identifying and extracting the privacy data based on the transfer learning technology;
The desensitization module is used for carrying out desensitization processing on the extracted privacy data according to a set desensitization strategy to obtain desensitized data;
The output module synchronizes the desensitized data to the data out-of-domain gateway interface, sets a data fusing threshold value, and normally outputs the desensitized data conforming to the fusing threshold value through the interface; the desensitized data which does not accord with the fusing threshold value is reported to the management center and a fusing mechanism is realized;
The output module monitors the flow of the out-of-domain by using the time sequence model and the firewall device; downloading the desensitized data source through the data downloading server information of the data downloading rule; the method comprises the following steps:
Acquiring a desensitization data out-of-domain access rule of a management center, and synchronously outputting the desensitization data through an interface;
establishing a related time sequence data model according to a data flow interface of desensitization data in a period of time;
Acquiring an internal firewall mechanism of a management center, and setting a data fusing threshold for preventing malicious recognition;
The desensitization data is normally output through the interface according with the setting of the fusing threshold value, is not met, and is reported to the management center to realize the fusing mechanism;
The time sequence data model is as follows:
In the above Representing text content in a website,/>Representing the probability of whether the text belongs to, and obtaining the text by time sequence data and a firewall/>For determining data out-of-domain gateway/>Whether or not it belongs to the abnormal data class/>If/>Indicating/>, within a certain period of timeBelonging to abnormal data/>。
5. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements a method of private data identification and desensitization according to any one of claims 1-3 when executing the computer program.
6. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements a method of private data identification and desensitization according to any of claims 1 to 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211741149.6A CN116049877B (en) | 2022-12-30 | 2022-12-30 | Method, system, equipment and storage medium for identifying and desensitizing private data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211741149.6A CN116049877B (en) | 2022-12-30 | 2022-12-30 | Method, system, equipment and storage medium for identifying and desensitizing private data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116049877A CN116049877A (en) | 2023-05-02 |
CN116049877B true CN116049877B (en) | 2024-05-28 |
Family
ID=86126868
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211741149.6A Active CN116049877B (en) | 2022-12-30 | 2022-12-30 | Method, system, equipment and storage medium for identifying and desensitizing private data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116049877B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109284631A (en) * | 2018-10-26 | 2019-01-29 | 中国电子科技网络信息安全有限公司 | A kind of document desensitization system and method based on big data |
CN111625858A (en) * | 2020-05-10 | 2020-09-04 | 武汉理工大学 | Intelligent multi-mode data desensitization method and device in vertical field |
CN111813808A (en) * | 2020-06-10 | 2020-10-23 | 云南电网有限责任公司 | Method and device for quickly desensitizing big data |
GB2600802A (en) * | 2020-11-09 | 2022-05-11 | Adobe Inc | Machine learning modeling for protection against online disclosure of sensitive data |
CN114710303A (en) * | 2020-12-17 | 2022-07-05 | 中国科学院计算机网络信息中心 | Super computing center threat identification method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110390641B (en) * | 2018-04-16 | 2023-12-01 | 阿里巴巴集团控股有限公司 | Image desensitizing method, electronic device and storage medium |
-
2022
- 2022-12-30 CN CN202211741149.6A patent/CN116049877B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109284631A (en) * | 2018-10-26 | 2019-01-29 | 中国电子科技网络信息安全有限公司 | A kind of document desensitization system and method based on big data |
CN111625858A (en) * | 2020-05-10 | 2020-09-04 | 武汉理工大学 | Intelligent multi-mode data desensitization method and device in vertical field |
CN111813808A (en) * | 2020-06-10 | 2020-10-23 | 云南电网有限责任公司 | Method and device for quickly desensitizing big data |
GB2600802A (en) * | 2020-11-09 | 2022-05-11 | Adobe Inc | Machine learning modeling for protection against online disclosure of sensitive data |
CN114710303A (en) * | 2020-12-17 | 2022-07-05 | 中国科学院计算机网络信息中心 | Super computing center threat identification method |
Non-Patent Citations (2)
Title |
---|
基于深度内容识别的数据脱敏合规检测平台研究与实现;梁群;;湖南邮电职业技术学院学报;20200615(02);全文 * |
数据脱敏技术的探究与实现;叶水勇;;电力信息与通信技术;20190415(第04期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN116049877A (en) | 2023-05-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | Network intrusion detection method based on PCA and Bayes algorithm | |
CN112468347B (en) | Security management method and device for cloud platform, electronic equipment and storage medium | |
CN113111951B (en) | Data processing method and device | |
Khan et al. | Digital forensics and cyber forensics investigation: security challenges, limitations, open issues, and future direction | |
CN111639355B (en) | Data security management method and system | |
Vast et al. | Artificial intelligence based security orchestration, automation and response system | |
Wang et al. | An unknown protocol syntax analysis method based on convolutional neural network | |
Liang et al. | FECC: DNS tunnel detection model based on CNN and clustering | |
CN117478403A (en) | Whole scene network security threat association analysis method and system | |
Yadav et al. | Big data hadoop: Security and privacy | |
CN116049877B (en) | Method, system, equipment and storage medium for identifying and desensitizing private data | |
Wang et al. | Application research of file fingerprint identification detection based on a network security protection system | |
Liu et al. | A research and analysis method of open source threat intelligence data | |
CN116738369A (en) | Traffic data classification method, device, equipment and storage medium | |
Lu et al. | One intrusion detection method based on uniformed conditional dynamic mutual information | |
[Retracted] Design of a Network Security Audit System Based on Log Data Mining | ||
CN114861205A (en) | Data classification-based privacy protection system with high safety performance | |
Garchery | User-centered intrusion detection using heterogeneous data | |
Richardson et al. | Anomaly detection in cyber network data using a cyber language approach | |
Bie et al. | Malicious mining behavior detection system of encrypted digital currency based on machine learning | |
CN118157996B (en) | Method and system for improving data security of temporary office local area network | |
Li et al. | Multi-View Feature Fusion for Ransomware Detection in Executable Files: Dynamic, Static, and Image Features | |
CN114401112B (en) | Bypass deployment real-time deep packet detection method for malicious traffic encrypted by TLS | |
Yu et al. | Research on Identification Method of Sensitive Data in Power System | |
Lakshmi et al. | Wlan intrusion detection system based on svm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |