CN116861459A - Credit scoring model modeling method and system based on privacy calculation - Google Patents
Credit scoring model modeling method and system based on privacy calculation Download PDFInfo
- Publication number
- CN116861459A CN116861459A CN202310821730.7A CN202310821730A CN116861459A CN 116861459 A CN116861459 A CN 116861459A CN 202310821730 A CN202310821730 A CN 202310821730A CN 116861459 A CN116861459 A CN 116861459A
- Authority
- CN
- China
- Prior art keywords
- data
- privacy
- model
- encryption
- unit
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000007405 data analysis Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims description 30
- 230000008569 process Effects 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 7
- 238000013480 data collection Methods 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000007477 logistic regression Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 abstract description 7
- 238000000586 desensitisation Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 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
- G06F21/602—Providing cryptographic facilities or services
-
- 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
- G06F21/62—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
- G06F21/6254—Protecting personal data, e.g. for financial or medical purposes by anonymising data, e.g. decorrelating personal data from the owner's identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention provides a credit score model modeling method and a credit score model modeling system based on privacy calculation, wherein the privacy calculation can be used for carrying out data analysis and modeling under the condition of not exposing sensitive data. In credit score modeling, privacy calculations are used to model where data is available and not visible. Specifically, the method comprises the steps of encrypting sensitive data by data encryption so as to protect the privacy of the data. The encryption algorithm may choose symmetric encryption or asymmetric encryption. Data desensitization: and (3) desensitizing the encrypted data to reduce the leakage risk of sensitive information. Privacy calculation: the encrypted and desensitized data is computed and analyzed using privacy computation techniques to generate a credit scoring model. Privacy calculations include secure multiparty calculations, homomorphic encryption. Model verification: through model verification and evaluation, the credit scoring model generated by privacy calculation is ensured to have higher accuracy and reliability, the privacy data of the user is protected, and meanwhile, accurate and reliable credit scoring service is provided.
Description
Technical Field
The invention relates to the field of computers, in particular to a credit score model modeling method and a credit score model modeling system based on privacy calculation.
Background
Existing credit scoring models are based primarily on the collection and analysis of personal information, but this approach tends to leak the user's private information. Thus, privacy calculations have emerged as a new type of calculation model.
However, there are some disadvantages in the use process of the existing credit scoring model, and the existing credit scoring model is mainly based on collection and analysis of personal information, but this way privacy information of users is easily leaked.
Therefore, the method and the system for modeling the credit scoring model based on the privacy calculation are improved, the privacy calculation can be carried out by processing personal data in the terminal, so that the privacy of the user can be protected, and meanwhile, the data analysis task can be completed.
Disclosure of Invention
The invention aims at: aiming at the problems of the existing background. In order to achieve the dual objective of credit scoring and privacy protection by performing computation on a user terminal, the present invention provides the following scheme: the credit score model modeling method based on privacy calculation and the system thereof comprise a user terminal module and a privacy calculation module, wherein the user terminal is used for collecting user data, processing the user data by an encryption module and importing the disturbed data into a model training module; the encryption module comprises a key generation unit, a data encryption unit and a data decryption unit;
the privacy computing module comprises safe multiparty computing and homomorphic encryption computing, wherein the safe multiparty computing performs data computing and analysis under the condition of multiparty participation, and meanwhile, data privacy is protected; the homomorphic encryption can perform data calculation and analysis in a ciphertext state, and meanwhile, data privacy is protected;
the model training module comprises a data collecting unit, a data characteristic extracting unit, a data analyzing unit and a model establishing unit, and is used for importing data into a model application algorithm module, and the model application algorithm module is used for calculating credit scores of users.
As a preferable scheme of the invention, a data collection unit in the model training module collects the credit score related data in the user terminal module, and a data feature extraction unit performs feature extraction on the data subjected to the differential privacy processing to convert the collected user information into a numerical feature.
As a preferable scheme of the invention, a data analysis unit learning algorithm in the model training module processes and optimizes the extracted numerical characteristics, and the processing optimization uses principal component analysis to perform dimension reduction processing on the characteristics.
As a preferred scheme of the invention, the key of the model training module is to carry out privacy protection on data, and model and optimize the data by utilizing a machine learning algorithm to obtain a reliable credit scoring model.
As a preferred scheme of the invention, the encryption module comprises a key generation unit for encrypting data, the key comprises a public key and a private key, the public key is used for encrypting the data, the private key only has independent use permission for decrypting the data, and the key is generated through a plurality of mathematical algorithms and comprises a large prime number decomposition unit, an euler function unit and a modular exponentiation unit, and the data encryption unit and the data decryption unit.
As a preferable scheme of the invention, the encryption process of the data encryption unit of the encryption module is to encrypt the plaintext data by using a public key to obtain the ciphertext data, and the secret key can carry out mathematical transformation on the plaintext data in the encryption process.
As a preferred scheme of the invention, the data decryption unit of the encryption module decrypts the encrypted ciphertext data by using the private key in the data decryption process to restore the encrypted ciphertext data to original plaintext data, and in the decryption process, the private key performs mathematical transformation on the ciphertext data, and only a person with the private key can decrypt the ciphertext data to restore the encrypted ciphertext data to original plaintext data.
A credit score model modeling method based on privacy calculation comprises the following steps: step 1: collecting user data including age, occupation and income information related data information of a user through a user terminal module;
step 2: noise disturbance is carried out on the encrypted data by utilizing differential privacy, so that the privacy of a user is protected, and the disturbed data is ensured to keep certain accuracy;
step 3: model training is carried out on the disturbed data transmission, and the credit score of the user is calculated by using the model on the user terminal.
As a preferable scheme of the invention, the model training in the step 3 establishes a logic unit, and the logic unit is used for fitting the characteristic variable and the target variable to obtain a logistic regression model so as to predict the classification result.
In the preferred scheme of the invention, in step 4, the credit score data is classified and estimated through a calculation network of nodes formed by the neural network.
Compared with the prior art, the invention has the beneficial effects that:
in the scheme of the invention: data analysis and modeling can be performed without exposing sensitive data through privacy calculations. In credit score modeling, privacy calculations are used to model where data is available and not visible. Specifically, the method comprises the steps of encrypting sensitive data by data encryption so as to protect the privacy of the data. The encryption algorithm may choose symmetric encryption or asymmetric encryption. Data desensitization: and (3) desensitizing the encrypted data to reduce the leakage risk of sensitive information. Privacy calculation: the encrypted and desensitized data is computed and analyzed using privacy computation techniques to generate a credit scoring model. Privacy calculations include secure multiparty calculations, homomorphic encryption. Model verification: through model verification and evaluation, the credit scoring model generated by privacy calculation is ensured to have higher accuracy and reliability, the privacy data of the user is protected, and meanwhile, accurate and reliable credit scoring service is provided.
Drawings
FIG. 1 is a flow chart provided by the present invention;
FIG. 2 is a flow chart of a model training module provided by the present invention;
FIG. 3 is a flowchart of an encryption module provided by the present invention;
fig. 4 is a flowchart of privacy calculation provided by the present invention.
Detailed Description
In order to make the objects, aspects and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be more fully described hereinafter with reference to the accompanying drawings. It will be apparent that the described embodiments are some, but not all, embodiments of the invention.
Thus, the following detailed description of the embodiments of the invention is not intended to limit the scope of the invention, as claimed, but is merely representative of some embodiments of the invention. All other embodiments obtained by those skilled in the art without making any creative effort based on the embodiments of the present invention are within the protection scope of the present invention, and it should be noted that the embodiments of the present invention and features and schemes of the embodiments may be combined with each other without collision: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
Example 1: a credit score model modeling method based on privacy calculation comprises the following steps: step 1: collecting user data including age, occupation and income information related data information of a user through a user terminal module;
step 2: noise disturbance is carried out on the encrypted data by utilizing differential privacy, so that the privacy of a user is protected, and the disturbed data is ensured to keep certain accuracy;
step 3: model training is carried out on the disturbed data transmission, and the credit score of the user is calculated by using the model on the user terminal.
And 3, building a logic unit through model training in the step, and fitting the characteristic variable and the target variable through the logic unit to obtain a logistic regression model so as to predict the classification result.
And 4, classifying and estimating credit score data through a calculation network of nodes formed by the neural network.
Example 2: referring to fig. 1-4, a credit score model modeling system based on privacy calculation includes a user terminal module and a privacy calculation module, wherein the user terminal is used for collecting user data, processing the user data by an encryption module, and importing the disturbed data into a model training module; the encryption module comprises a key generation unit, a data encryption unit and a data decryption unit;
the privacy computing module comprises safe multiparty computing and homomorphic encryption computing, wherein the safe multiparty computing performs data computing and analysis under the condition of multiparty participation, and meanwhile, data privacy is protected; the homomorphic encryption can perform data calculation and analysis in a ciphertext state, and meanwhile, data privacy is protected;
the model training module comprises a data collecting unit, a data characteristic extracting unit, a data analyzing unit and a model establishing unit, and is used for importing data into a model application algorithm module, and the model application algorithm module is used for calculating credit scores of users.
The data collection unit in the model training module collects the credit score related data in the user terminal module, and the data after differential privacy processing is subjected to feature extraction through the data feature extraction unit, so that the collected user information is converted into numerical features.
The data analysis unit in the model training module processes and optimizes the extracted numerical characteristics, the processing and optimizing process uses principal component analysis to perform dimension reduction processing on the characteristics, and the training and modeling of the model are completed in cloud encryption.
The key of the model training module is that the privacy protection is carried out on the data, meanwhile, the machine learning algorithm is utilized to model and optimize the data, a reliable credit scoring model is obtained, the training and modeling work of the model are completed at the cloud, the privacy of a user is fully protected, and the risk of information leakage of the user is avoided.
The encryption module comprises a key generation unit for encrypting data, wherein the key comprises a public key and a private key, the public key is used for encrypting the data, the private key only has independent use permission for decrypting the data, and the key is generated through a plurality of mathematical algorithms and comprises a large prime number decomposition unit, an Euler function unit and a modular exponentiation unit, and the data encryption unit and the data decryption unit.
The encryption process of the data encryption unit of the encryption module is to encrypt plaintext data by using a public key to obtain ciphertext data, and the secret key performs mathematical transformation on the plaintext data in the encryption process.
And the data decryption unit of the encryption module decrypts the encrypted ciphertext data by using a private key in the data decryption process to restore the encrypted ciphertext data into original plaintext data, and in the decryption process, the private key performs mathematical transformation on the ciphertext data, and only a person with the private key can decrypt the ciphertext data to restore the original plaintext data.
Privacy calculations can be data analyzed and modeled without exposing sensitive data. In credit score modeling, privacy calculations can be modeled in cases where data is available and not visible by the following steps: step 1, data encryption: sensitive data is encrypted to protect data privacy. The encryption algorithm may choose symmetric encryption or asymmetric encryption.
Step 2, data desensitization: and (3) desensitizing the encrypted data to reduce the leakage risk of sensitive information. The data desensitization method comprises data disturbance, data noise adding, data shielding and the like.
Step 3, privacy calculation: the encrypted and desensitized data is computed and analyzed using privacy computation techniques to generate a credit scoring model. Common privacy calculation methods include secure multi-party calculation, homomorphic encryption, and differential privacy.
Step 4, model verification: and through model verification and evaluation, the credit scoring model generated by privacy calculation is ensured to have higher accuracy and reliability.
Through the steps, the privacy calculation can realize credit score modeling under the condition that the data is available and invisible, protect the privacy data of the user and simultaneously provide accurate and reliable credit score service.
Privacy calculations are a technique to preserve data privacy and allow data analysis and processing without exposing sensitive data. The specific calculation method and steps of the privacy calculation are different from one privacy calculation technology to another, and the specific calculation method and steps are introduced below by two common privacy calculations of secure multiparty calculation and homomorphic encryption.
Secure multiparty computing: the secure multiparty computation performs data computation and analysis with multiparty participation while protecting data privacy. The specific calculation steps of the secure multiparty calculation are as follows:
(1) The preparation stage: the parties participating in the calculation perform identity verification and key negotiation according to a security protocol to ensure secure communication and calculation.
(2) An input stage: each participant encrypts the input data and sends the encrypted ciphertext to the other participants.
(3) And (3) a calculation stage: and each party uses the ciphertext to calculate, encrypts the calculation result and sends the calculation result to other parties.
(4) Output stage: each party decrypts the encrypted calculation result to obtain a final calculation result.
Homomorphic encryption can perform data calculation and analysis in a ciphertext state, and meanwhile data privacy is protected. The specific calculation steps of homomorphic encryption are as follows:
(1) Data encryption: the data owner encrypts the data to generate ciphertext.
(2) Homomorphism calculation: and the data analyzer calculates and analyzes the ciphertext by using a homomorphic encryption algorithm to generate a ciphertext of a calculation result.
(3) Decryption output: and the data analyzer decrypts the ciphertext of the calculation result to obtain a final calculation result.
In the using process, the invention carries out encryption module processing on the user data and leads the disturbed data into a model training module; the encryption module comprises a key generation unit, a data encryption unit and a data decryption unit; the encryption module comprises a key generation unit for encrypting data, wherein the key comprises a public key and a private key, the public key is used for encrypting the data, the private key only has independent use permission for decrypting the data, and the key is generated through a plurality of mathematical algorithms and comprises a large prime number decomposition unit, an Euler function unit and a modular exponentiation unit, and the data encryption unit and the data decryption unit. The encryption process of the data encryption unit of the encryption module is to encrypt plaintext data by using a public key to obtain ciphertext data, and the secret key performs mathematical transformation on the plaintext data in the encryption process. And the data decryption unit of the encryption module decrypts the encrypted ciphertext data by using a private key in the data decryption process to restore the encrypted ciphertext data into original plaintext data, and in the decryption process, the private key performs mathematical transformation on the ciphertext data, and only a person with the private key can decrypt the ciphertext data to restore the original plaintext data.
The model training module is used for carrying out model training and establishing a credit scoring model at the cloud, and comprises a data collecting unit, a data characteristic extracting unit, a data analyzing unit and a model establishing unit, wherein the model training module is used for importing data into a model application algorithm module, and the model application algorithm module is used for calculating the credit score of a user by using the model on a user terminal. The data collection unit in the model training module collects the credit score related data in the user terminal module, and the data after differential privacy processing is subjected to feature extraction through the data feature extraction unit, so that the collected user information is converted into numerical features. The data analysis unit in the model training module processes and optimizes the extracted numerical characteristics, the processing optimization uses a principal component analysis method to perform dimension reduction processing on the characteristics, and the data encrypted by differential privacy is subjected to noise disturbance so as to protect user privacy.
The above embodiments are only for illustrating the present invention and not for limiting the scheme described in the present invention, and although the present invention has been described in detail in the present specification with reference to the above embodiments, the present invention is not limited to the above specific embodiments, and thus any modifications or equivalents thereof are possible; all such modifications and variations which do not depart from the spirit and scope of the invention are intended to be included within the scope of the invention as defined in the appended claims.
Claims (10)
1. The credit score model modeling system based on privacy calculation is characterized by comprising a user terminal module and a privacy calculation module, wherein the user terminal is used for collecting user data, processing the user data by an encryption module and importing the disturbed data into a model training module; the encryption module comprises a key generation unit, a data encryption unit and a data decryption unit;
the privacy computing module comprises safe multiparty computing and homomorphic encryption computing, wherein the safe multiparty computing performs data computing and analysis under the condition of multiparty participation, and meanwhile, data privacy is protected; the homomorphic encryption can perform data calculation and analysis in a ciphertext state, and meanwhile, data privacy is protected;
the model training module comprises a data collecting unit, a data characteristic extracting unit, a data analyzing unit and a model establishing unit, and is used for importing data into a model application algorithm module, and the model application algorithm module is used for calculating credit scores of users.
2. The privacy calculation-based credit score model modeling system of claim 1, wherein the data collection unit in the model training module collects credit score related data in the user terminal module, and the data after differential privacy processing is subjected to feature extraction by the data feature extraction unit to convert the collected user information into numerical features.
3. The privacy computation-based credit score model modeling system of claim 2, wherein the data analysis unit learning algorithm in the model training module processes and optimizes the extracted numerical features.
4. A credit score model modeling system based on privacy calculations as claimed in claim 3, wherein the model training module is critical to privacy protection of data, and simultaneously uses a machine learning algorithm to model and optimize the data to obtain the credit score model.
5. The system of claim 4, wherein the encryption module comprises a key generation unit for encrypting data, the key comprises a public key and a private key, the public key is used for encrypting the data, the private key has independent use authority for decrypting the data, the key is generated by a plurality of mathematical algorithms, and the key comprises a large prime number decomposition, an euler function and a modular exponentiation, a data encryption unit and a data decryption unit.
6. The system of claim 5, wherein the encryption process of the data encryption unit of the encryption module encrypts plaintext data with a public key to obtain ciphertext data, and the secret key performs mathematical transformation on the plaintext data during the encryption process.
7. The system of claim 6, wherein the data decryption unit of the encryption module decrypts the encrypted ciphertext data using a private key to restore the encrypted ciphertext data to original plaintext data, and wherein the private key mathematically transforms the ciphertext data during decryption, and only a person having the private key can decrypt the ciphertext data to restore the ciphertext data to the original plaintext data.
8. The credit score model modeling method based on privacy calculation is characterized by comprising the following steps of: step 1: collecting user data including age, occupation and income information related data information of a user through a user terminal module;
step 2: noise disturbance is carried out on the encrypted data by utilizing differential privacy, so that the privacy of a user is protected, and the accuracy of the disturbed data is ensured;
step 3: model training is carried out on the disturbed data transmission, and the credit score of the user is calculated by using the model on the user terminal.
9. The method for modeling a credit score model based on privacy calculation according to claim 8, wherein the model training in the step 3 establishes a logic unit, and the logic unit fits the feature variable and the target variable to obtain a logistic regression model, so as to predict the classification result.
10. The method of claim 9, wherein in step 4, the credit score data is classified and estimated by a computing network of nodes formed by a neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310821730.7A CN116861459A (en) | 2023-07-05 | 2023-07-05 | Credit scoring model modeling method and system based on privacy calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310821730.7A CN116861459A (en) | 2023-07-05 | 2023-07-05 | Credit scoring model modeling method and system based on privacy calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116861459A true CN116861459A (en) | 2023-10-10 |
Family
ID=88218490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310821730.7A Pending CN116861459A (en) | 2023-07-05 | 2023-07-05 | Credit scoring model modeling method and system based on privacy calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116861459A (en) |
-
2023
- 2023-07-05 CN CN202310821730.7A patent/CN116861459A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084063B (en) | Gradient descent calculation method for protecting private data | |
| CN111259443B (en) | PSI (program specific information) technology-based method for protecting privacy of federal learning prediction stage | |
| CN113537633B (en) | Prediction method, device, equipment, medium and system based on longitudinal federal learning | |
| Barni et al. | SEMBA: secure multi‐biometric authentication | |
| Tan et al. | High-secure fingerprint authentication system using ring-LWE cryptography | |
| CN101331706A (en) | Secure threshold decryption protocol computation | |
| CN110400162B (en) | Data processing method, device, server and system | |
| Alberto Torres et al. | Privacy-preserving biometrics authentication systems using fully homomorphic encryption | |
| CN112185395B (en) | Federal voiceprint recognition method based on differential privacy | |
| CN110674941B (en) | Data encryption transmission method and system based on neural network | |
| Torres et al. | Effectiveness of fully homomorphic encryption to preserve the privacy of biometric data | |
| CN112532383B (en) | Privacy protection calculation method based on secret sharing | |
| Liu et al. | An efficient biometric identification in cloud computing with enhanced privacy security | |
| CN115913537A (en) | Data intersection method and system based on privacy protection and related equipment | |
| CN111490995A (en) | Model training method and device for protecting privacy, data processing method and server | |
| CN116561787A (en) | Training method and device for visual image classification model and electronic equipment | |
| Luo et al. | Anonymous biometric access control based on homomorphic encryption | |
| CN112380404B (en) | Data filtering method, device and system | |
| CN105897401B (en) | General differential power consumption analysis method and system based on bit | |
| Eltaieb et al. | Efficient implementation of cancelable face recognition based on elliptic curve cryptography | |
| Hamian et al. | Blockchain-based User Re-enrollment for Biometric Authentication Systems | |
| CN116861459A (en) | Credit scoring model modeling method and system based on privacy calculation | |
| CN115456766A (en) | Credit risk prediction method and device | |
| CN111475690B (en) | Character string matching method and device, data detection method and server | |
| CN114547684A (en) | Method and device for protecting multi-party joint training tree model of private data |
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 |