CN115761840A - Face recognition protection system based on big data platform - Google Patents
Face recognition protection system based on big data platform Download PDFInfo
- Publication number
- CN115761840A CN115761840A CN202211305143.4A CN202211305143A CN115761840A CN 115761840 A CN115761840 A CN 115761840A CN 202211305143 A CN202211305143 A CN 202211305143A CN 115761840 A CN115761840 A CN 115761840A
- Authority
- CN
- China
- Prior art keywords
- module
- face
- distance
- face recognition
- verification
- 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
Classifications
-
- 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
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a face recognition protection system based on a big data platform, which comprises a data storage module and a face recognition module, wherein the information storage module is used for storing a face information image and establishing a face template database, the face recognition module is used for carrying out face recognition according to image information input by a client, the face recognition module is connected with the data storage module through a network, the information storage module comprises a client registration module, an original image input module, a feature extraction module, an encryption transmission module, a template database establishment module and an identity verification module, the face recognition module comprises a face verification module and a face identification module, the face verification module comprises a single distance calculation module, a distance comparison module and a verification result output module, and the face identification module comprises a plurality of distance calculation modules, a minimum comparison module and a identification result output module.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a face recognition protection system based on a big data platform.
Background
The face recognition technology has strong specialty, the face information of the user can be collected at extremely low cost due to the asymmetry of the information caused by the specialty, and with the wide application of the face recognition technology, the privacy safety of the user is gradually controversial. The face recognition system collects face data of a user for commercial use, the face data are generally uploaded to the cloud end through a network, and once the face data are leaked, the privacy of the user is greatly damaged. Therefore, it is necessary to design a face recognition protection system based on a big data platform with high security and practicability.
Disclosure of Invention
The invention aims to provide a face recognition protection system based on a big data platform to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: the face recognition protection system based on the big data platform comprises a data storage module and a face recognition module, wherein the information storage module is used for storing face information images and establishing a face template database, the face recognition module is used for carrying out face recognition according to image information input by a client, and the face recognition module is in network connection with the data storage module.
According to the technical scheme, the information storage module comprises a client registration module, an original image input module, a feature extraction module, an encryption transmission module, a template database establishment module and an identity verification module, wherein the client registration module is used for a user to register the client through a face image and identity information, the original image input module is used for inputting the original image through a Facenet deep learning model, the feature extraction module is used for extracting features of the face image, the encryption transmission module is used for encrypting and transmitting extracted feature vectors to a server, the template database establishment module is used for establishing the face template database according to encrypted data, the identity verification module is used for verifying the identity information of the user, and the encryption transmission module is in network connection with the template database establishment module.
According to the technical scheme, the face recognition module comprises a face verification module and a face identification module, the face verification module is used for judging whether the face image of the user is matched with a certain template in the database or not according to the face image of the user, the face identification module is used for judging whether the user exists in the database or not according to the face image of the user, the face verification module is connected with the identity verification module through a network, and the face identification module is connected with the face verification module through a network.
According to the technical scheme, the face verification module comprises a single distance calculation module, a distance comparison module and a verification result output module, wherein the single distance calculation module is used for calculating the squared Euclidean distance between a test vector and another template feature vector, the distance comparison module is used for comparing the calculated distance with a set threshold value, the verification result output module is used for outputting a final verification result, and the distance comparison module is in network connection with the single distance calculation module;
the face identification module comprises a plurality of distance calculation modules, a minimum value comparison module and an identification result output module, wherein the distance calculation modules are used for calculating the squared Euclidean distance between a test vector and all ciphertexts in a face template database, the minimum value comparison module is used for comparing the minimum distance value in the calculation result with a set threshold value, the identification result output module is used for outputting the final identification result, and the minimum value comparison module is in network connection with the distance calculation modules.
According to the technical scheme, the operation method of the face recognition protection system mainly comprises the following steps:
step S1: the method comprises the steps of outputting n-dimensional real-valued characteristic vectors representing original images by using the original images as input information through a Facenet deep learning model, encrypting all real-valued characteristic vectors and then transmitting the encrypted real-valued characteristic vectors to a server to establish a face template database;
step S2: when the face verification or identification is required to be carried out by the client, the user information and the image are sent to the server for identity verification;
and step S3: the face verification module calculates the squared Euclidean distance between the test vector and the other template feature vector, compares the distance with a set threshold value and outputs a verification result;
and step S4: the face identification module calculates the squared Euclidean distance between the test vector and all the ciphertexts in the face template database, compares the minimum distance value in the calculation result with a set threshold value, and outputs an identification result.
According to the above technical solution, the step S1 specifically includes the following steps:
step S11: the client acquires a face image of a user and an identity tag thereof through a camera, and extracts a feature vector from the face image through a Facenet deep learning model;
step S12: the client encrypts the feature vector of the user i into a single ciphertext by using a single instruction multiple data stream technology;
step S13: the encrypted feature vector and the corresponding label (i, c) thereof i ) Transmitting to a server;
step S14: the server establishes a registration template database comprising N users, stores the data transmitted by the client and completes registration.
According to the above technical solution, the authentication in step S2 specifically includes: the client labels the identity as i 0 Test vector v of 0 ＝(v 01 ，v 02 ，…v 0n ) Encrypted as c with public key 0 While encrypting the session key as c with the public key k ；
The client side sends the ciphertext c k 、c 0 And identity tag i 0 And transmitting the face identification information to a server, receiving the face identification information by the server, and then carrying out identity authentication on the face identification information, wherein face authentication and identification can be carried out after the face identification information is successfully authenticated, otherwise, subsequent operation is not carried out.
According to the above technical solution, the step S3 further comprises the steps of:
step S31: the server searches the encrypted characteristic vectors with the same label in the template database according to the transmitted identity label;
step S32: after the same label is matched, calculating the squared Euclidean distance d of the characteristic vectors of the two pictures with the same identity label;
step S33: after the distance is calculated, the comparison operation of the threshold value is carried out between the server and the password server, and the ciphertext c of the square Euclidean distance is subjected to random mask technology d Decrypting to obtain plaintext distance d, comparing d with set threshold value d 0 Comparing and outputtingAnd (6) outputting a verification result.
According to the technical scheme, compared with the step S3, the specific step of the step S4 is only to repeat the steps S31-S32, the identity tag is not required to be inquired when the square Euclidean distance is calculated, the square Euclidean distance is calculated between the comparison information and all information in the database, the step S33 is executed again, the minimum distance is extracted for comparison, and finally an output result is returned.
According to the above technical solution, the calculation of the squared euclidean distance in step S32 is specifically:
cipher text c of squared euclidean distance in step S33 d The method comprises the following specific steps:
compared with the prior art, the invention has the following beneficial effects: according to the invention, the data storage module and the face recognition module are arranged, the client encrypts and uploads images by using a single-instruction-multiple-data-stream technology, and the face images are converted into the feature vectors through the Facenet deep learning model under a client-server-password server three-party model, so that the squared Euclidean distance between the two feature vectors directly corresponds to the face similarity, and the face recognition problem is simplified; the server carries out face recognition in a ciphertext state and returns a recognition result to the client under the assistance of the password server, in the process, the server and the password server cannot acquire any information such as a face image, an access mode, an intermediate result and a final output result, and the client cannot acquire other information except the final result, so that the safety of face data and the privacy of a user are ensured.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of the system module composition of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution: the face recognition protection system based on the big data platform comprises a data storage module and a face recognition module, wherein the information storage module is used for storing a face information image and establishing a face template database, the face recognition module is used for carrying out face recognition according to image information input by a client, the face recognition module is connected with the data storage module through a network, the client encrypts and uploads the image by using a single-instruction multiple-data-stream technology through the data storage module and the face recognition module, and the face image is converted into a feature vector through a Facenet deep learning model under a client-server-password server three-way model, so that a squared Euclidean distance between the two feature vectors directly corresponds to face similarity, and the face recognition problem is simplified; the server performs face recognition in a ciphertext state and returns a recognition result to the client under the assistance of the password server, in the process, the server and the password server cannot acquire any information such as a face image, an access mode, an intermediate result and a final output result, and the client cannot acquire other information except the final result, so that the safety of face data and the privacy of a user are ensured.
The information storage module comprises a client registration module, an original image input module, a feature extraction module, an encryption transmission module, a template database establishment module and an identity verification module, wherein the client registration module is used for performing client registration on a user through a face image and identity information, the original image input module is used for inputting the original image through a Facenet deep learning model, the feature extraction module is used for performing feature extraction on the face image, the encryption transmission module is used for encrypting and transmitting extracted feature vectors to a server, the template database establishment module is used for establishing a face template database according to encrypted data, the identity verification module is used for verifying the identity information of the user, and the encryption transmission module is in network connection with the template database establishment module.
The face recognition module comprises a face verification module and a face identification module, the face verification module is used for judging whether the face image of the user is matched with a certain template in the database or not according to the face image of the user, the face identification module is used for judging whether the user exists in the database or not according to the face image of the user, the face verification module is connected with the identity verification module through a network, and the face identification module is connected with the face verification module through a network.
The face verification module comprises a single distance calculation module, a distance comparison module and a verification result output module, wherein the single distance calculation module is used for calculating the squared Euclidean distance between the test vector and the other template feature vector, the distance comparison module is used for comparing the calculated distance with a set threshold value, the verification result output module is used for outputting a final verification result, and the distance comparison module is in network connection with the single distance calculation module;
the face identification module comprises a plurality of distance calculation modules, a minimum value comparison module and an identification result output module, the distance calculation modules are used for calculating the squared Euclidean distance between a test vector and all ciphertexts in a face template database, the minimum value comparison module is used for comparing the minimum distance value in the calculation result with a set threshold value, the identification result output module is used for outputting the final identification result, and the minimum value comparison module is in network connection with the distance calculation modules.
The operation method of the face recognition protection system mainly comprises the following steps:
step S1: using an original image as input information through a Facenet deep learning model, outputting an n-dimensional real-valued feature vector representing the original image, encrypting all real-valued feature vectors and transmitting the encrypted real-valued feature vectors to a server, and establishing a face template database;
step S2: when the face verification or identification is required to be carried out by the client, the user information and the image are sent to the server for identity verification;
and step S3: the face verification module calculates a squared Euclidean distance between the test vector and another template feature vector, compares the distance with a set threshold value and outputs a verification result;
and step S4: the face identification module calculates the squared Euclidean distance between the test vector and all the ciphertexts in the face template database, compares the minimum distance value in the calculation result with a set threshold value, and outputs an identification result.
The step S1 specifically includes the following steps:
step S11: the client acquires the face image of the user and the identity tag of the user through the camera, extracts the feature vector through a Facenet deep learning model, and expresses the feature vector as v i ＝(v i1 ，v i2 ，…v in )；
Step S12: the client encrypts the characteristic vector of the user i into a single ciphertext by using a single instruction multiple data stream technology, and the encrypted vector is represented as c i ＝Enc(v i1 ，v i2 ，…v in ) Wherein Enc () represents a symmetric cryptographic algorithm operation;
step S13: the feature vector after encryption and the corresponding label (i, c) thereof i ) Transmitting to a server;
step S14: the server establishes a registration template database comprising N users, stores the data transmitted by the client and completes registration.
The identity authentication in the step S2 specifically includes: the client end labels the identity as i 0 Test vector v of 0 ＝(v 01 ，v 02 ，…v 0n ) Encrypted as c with public key 0 While encrypting the session key with the public key to c k ；
The client side sends the ciphertext c k 、c 0 And an identity tag i 0 The face identification is transmitted to a server, the server performs identity authentication after receiving the face identification, face authentication and identification can be performed after the face identification is successful, and otherwise, follow-up operation is not performedThe method and the device protect the safety of privacy data among participants, prevent the private data of the face of the client for face recognition from being directly exposed to the server, and prevent the client from acquiring the private data of the server by utilizing data directions such as intermediate values, recognition results and the like.
Step S3 further comprises the steps of:
step S31: the server searches the encrypted characteristic vectors with the same label in the template database according to the transmitted identity label;
step S32: after the same label is matched, calculating the squared Euclidean distance d of the characteristic vectors of the two pictures with the same identity label, mapping the face to a multidimensional space by a Facenet deep learning model, representing an original image by n-dimensional characteristic vectors, so that the squared Euclidean distance between the two characteristic vectors directly corresponds to the face similarity, and comparing the squared Euclidean distance of the two encrypted face pictures with a set threshold value, so that the face recognition problem can be simplified, wherein the shorter the distance is, the higher the similarity is;
step S33: after the distance is calculated, the comparison operation of the threshold value is carried out between the server and the password server, and the cipher text c of the squared Euclidean distance is processed by the random mask technology d Decrypting to obtain plaintext distance d, and in the server, square Euclidean distance cipher text c d Subtract vector (r) 1 ，r 2 ，…r n-1 ) To obtain a ciphertext c r Where r is a random number in plaintext space and the squared euclidean distance is masked by a random mask in message space so that the server cannot obtain any information about squared euclidean distance d, c r Sending the ciphertext to a password server, decrypting the ciphertext by the password server after receiving the ciphertext to obtain d, and comparing d with a set threshold value d 0 Comparing, outputting a verification result, after receiving the output result, the password server encrypts an output conversion table and an output label by using a session key, converts the output conversion table and the output label into a ciphertext and sends the ciphertext to the server, the server with the random number r and the password server carry out a forgotten transmission protocol to obtain an input value, the server sends the output label and the output conversion table to the client, and the client decodes the output label and the output conversion table by using the session keyEncrypting to obtain an output conversion table in a plaintext, comparing the output label with the conversion table, and outputting a verification result; the face authentication method and the face authentication system ensure that the server and the password server cannot acquire any information related to the face data and the authentication result of the user when the face authentication service is provided, and improve the safety.
Step S4, compared with step S3, the specific steps of steps S31-S32 are repeated, and when the squared euclidean distance is calculated, the identity tag is not queried, the squared euclidean distance is calculated between the comparison information and all the information in the database, step S33 is executed again, the minimum distance is extracted for comparison, and finally, the output result is returned.
The calculation of the squared euclidean distance in step S32 is specifically:
wherein v = (v) 1 ，v 2 ，…，v n )，w＝(w 1 ，w 2 ，…，w n ) Respectively corresponding face image feature vectors of the users v and w;
ciphertext c of squared euclidean distance in step S33 d The method comprises the following specific steps:
it should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described above, or equivalents may be substituted for elements thereof. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. Face identification protection system based on big data platform includes data storage module and face identification module, its characterized in that: the information storage module is used for storing face information images and establishing a face template database, the face recognition module is used for carrying out face recognition according to image information input by a client, and the face recognition module is connected with the data storage module through a network.
2. The face recognition protection system based on big data platform as claimed in claim 1, wherein: the information storage module comprises a client registration module, an original image input module, a feature extraction module, an encryption transmission module, a template database establishment module and an identity verification module, wherein the client registration module is used for a user to register a client through a face image and identity information, the original image input module is used for inputting the original image through a Facenet deep learning model, the feature extraction module is used for extracting features of the face image, the encryption transmission module is used for encrypting and transmitting extracted feature vectors to a server, the template database establishment module is used for establishing the face template database according to encrypted data, the identity verification module is used for verifying the identity information of the user, and the encryption transmission module is in module network connection with the template database.
3. The face recognition protection system based on the big data platform as claimed in claim 2, wherein: the face recognition module comprises a face verification module and a face identification module, the face verification module is used for judging whether the face image of the user is matched with a certain template in the database or not according to the face image of the user, the face identification module is used for judging whether the user exists in the database or not according to the face image of the user, the face verification module is in network connection with the identity verification module, and the face identification module is in network connection with the face verification module.
4. The big data platform based face recognition protection system according to claim 3, wherein: the face verification module comprises a single distance calculation module, a distance comparison module and a verification result output module, wherein the single distance calculation module is used for calculating a squared Euclidean distance between a test vector and another template feature vector, the distance comparison module is used for comparing the calculated distance with a set threshold value, the verification result output module is used for outputting a final verification result, and the distance comparison module is connected with the single distance calculation module through a network;
the face identification module comprises a plurality of distance calculation modules, a minimum value comparison module and an identification result output module, wherein the distance calculation modules are used for calculating the squared Euclidean distance between a test vector and all ciphertexts in a face template database, the minimum value comparison module is used for comparing the minimum distance value in the calculation result with a set threshold value, the identification result output module is used for outputting the final identification result, and the minimum value comparison module is in network connection with the distance calculation modules.
5. The big data platform based face recognition protection system according to claim 4, wherein: the operation method of the face recognition protection system mainly comprises the following steps:
step S1: the method comprises the steps of outputting n-dimensional real-valued characteristic vectors representing original images by using the original images as input information through a Facenet deep learning model, encrypting all real-valued characteristic vectors and then transmitting the encrypted real-valued characteristic vectors to a server to establish a face template database;
step S2: when the face verification or identification is required to be carried out by the client, the user information and the image are sent to the server for identity verification;
and step S3: the face verification module calculates the squared Euclidean distance between the test vector and the other template feature vector, compares the distance with a set threshold value and outputs a verification result;
and step S4: and the face identification module calculates the squared Euclidean distance between the test vector and all the ciphertexts in the face template database, compares the minimum distance value in the calculation result with a set threshold value and outputs an identification result.
6. The big data platform based face recognition protection system according to claim 5, wherein: the step S1 specifically includes the steps of:
step S11: the client acquires a face image of a user and an identity tag thereof through a camera, and extracts a feature vector from the face image through a Facenet deep learning model;
step S12: the client encrypts the feature vector of the user i into a single ciphertext by using a single instruction multiple data stream technology;
step S13: the encrypted feature vector and the corresponding label (i, c) thereof i ) Transmitting to a server;
step S14: the server establishes a registration template database comprising N users, stores the data transmitted by the client and completes registration.
7. The big data platform based face recognition protection system according to claim 6, wherein: the identity authentication in the step S2 specifically includes: the client labels the identity as i 0 Test vector v of 0 ＝(v 01 ，v 02 ，…v 0n ) Encrypted as c with public key 0 While encrypting the session key with the public key to c k (ii) a The client side sends the ciphertext c k 、c 0 And identity tag i 0 The face identification is transmitted to a server, the server performs identity authentication after receiving the face identification, and face identification and discrimination can be performed after successful authentication, otherwise, face identification is not performedAnd carrying out subsequent operations.
8. The big data platform based face recognition protection system according to claim 7, wherein: the step S3 further comprises the steps of:
step S31: the server searches the encrypted characteristic vectors with the same label in the template database according to the transmitted identity label;
step S32: after the same label is matched, calculating the squared Euclidean distance d of the characteristic vectors of the two pictures with the same identity label;
step S33: after the distance is calculated, the comparison operation of the threshold value is carried out between the server and the password server, and the ciphertext c of the square Euclidean distance is subjected to random mask technology d Decrypting to obtain plaintext distance d, comparing d with set threshold value d 0 And comparing and outputting a verification result.
9. The face recognition protection system based on the big data platform according to claim 8, wherein: compared with the step S3, the specific step of the step S4 is to repeat the steps S31-S32, when the square Euclidean distance is calculated, the identity label is not inquired, the square Euclidean distance is calculated between the comparison information and all information in the database, the step S33 is executed again, the minimum distance is extracted for comparison, and finally an output result is returned.
10. The face recognition protection system based on the big data platform as claimed in claim 9, wherein: the calculation of the squared euclidean distance in step S32 is specifically:
cipher text c of squared euclidean distance in step S33 d The method specifically comprises the following steps:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211305143.4A CN115761840A (en) | 2022-10-24 | 2022-10-24 | Face recognition protection system based on big data platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211305143.4A CN115761840A (en) | 2022-10-24 | 2022-10-24 | Face recognition protection system based on big data platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115761840A true CN115761840A (en) | 2023-03-07 |
Family
ID=85353068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211305143.4A Pending CN115761840A (en) | 2022-10-24 | 2022-10-24 | Face recognition protection system based on big data platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115761840A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116935479A (en) * | 2023-09-15 | 2023-10-24 | 纬领(青岛)网络安全研究院有限公司 | Face recognition method and device, electronic equipment and storage medium |
| CN117235694A (en) * | 2023-09-14 | 2023-12-15 | 黑龙江都越科技有限公司 | Login system and method based on face recognition big data |
-
2022
- 2022-10-24 CN CN202211305143.4A patent/CN115761840A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117235694A (en) * | 2023-09-14 | 2023-12-15 | 黑龙江都越科技有限公司 | Login system and method based on face recognition big data |
| CN116935479A (en) * | 2023-09-15 | 2023-10-24 | 纬领(青岛)网络安全研究院有限公司 | Face recognition method and device, electronic equipment and storage medium |
| CN116935479B (en) * | 2023-09-15 | 2023-12-15 | 纬领(青岛)网络安全研究院有限公司 | Face recognition method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108446680B (en) | Privacy protection method and system in face authentication system based on edge calculation | |
| CN101057448B (en) | Securely computing a similarity measure | |
| CN109802942B (en) | Voiceprint authentication method with privacy protection function | |
| CN115761840A (en) | Face recognition protection system based on big data platform | |
| CN1860724B (en) | Method for identification | |
| WO2017164159A1 (en) | 1:n biometric authentication, encryption, signature system | |
| Gomez-Barrero et al. | Privacy-preserving comparison of variable-length data with application to biometric template protection | |
| EP1489551A2 (en) | Biometric authentication system employing various types of biometric data | |
| CN115336223A (en) | Optimized private biometric matching | |
| CN101420301A (en) | Human face recognizing identity authentication system | |
| CN109165523A (en) | Identity identifying method and system, terminal device, server and storage medium | |
| CN109165581A (en) | A kind of secret protection face identification method based on homomorphic cryptography | |
| CN105046234A (en) | Invisible recognition method used for human face image in cloud environment and based on sparse representation | |
| CN112101531B (en) | Neural network model training method, device and system based on privacy protection | |
| CN114093001A (en) | Face recognition method for protecting privacy security | |
| CN105553980A (en) | Safety fingerprint identification system and method based on cloud computing | |
| CN108073820A (en) | Security processing, device and the mobile terminal of data | |
| CN104639528A (en) | DBA (database administrator) mobile client counterattack method and DBA mobile client counterattack device | |
| CN114996727A (en) | Biological feature privacy encryption method and system based on palm print and palm vein recognition | |
| CN111698253A (en) | Computer network safety system | |
| CN114065169B (en) | Privacy protection biometric authentication method and device and electronic equipment | |
| CN116545774A (en) | Audio and video conference security method and system | |
| Jin et al. | Privacy preserving face identification in the cloud through sparse representation | |
| CN104715537A (en) | Encryption and decryption method based on digital tags | |
| CN114090994A (en) | Face recognition authentication method and system based on block chain |
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 |