A secure face recognition method, system, device and storage medium

Abstract

The present invention discloses a secure face recognition method, system, device and storage medium. The method comprises the following steps: performing key matching according to a subject library key index to obtain a corresponding symmetric key, increasing the security of private data through a one-to-one key pair, decrypting a database's face feature ciphertext according to the symmetric key to obtain the database's face feature plaintext; performing key matching according to a user ID to obtain a user public key corresponding to the user's private key, decrypting the user's face feature data ciphertext according to the user public key to obtain the user's face feature data plaintext; comparing the user's face feature data plaintext with the face feature plaintext in the database to obtain a face recognition result, sending the face recognition result to an authentication server, so that the authentication server sends the face recognition result to a terminal according to the user ID, reducing the risk of information leakage during face recognition use by performing data decryption only when comparing face feature data, and improving the security of private data.

Description

Technical Field

[0001] The present invention relates to the technical field related to face recognition, and in particular to a secure face recognition method, system, device and storage medium. Background Art

[0002] Face recognition is a biometric technology that uses facial features to identify people. It uses a camera or camcorder to capture images or video streams containing faces, automatically detects faces in the images, and then performs facial recognition on the detected faces.

[0003] Facial recognition is primarily used for identity verification. It extracts biometric facial information from images or video streams and compares it with a facial feature database in real time, enabling rapid identification. Facial recognition technology is widely used in government, military, public security, finance, e-commerce, social management, public services, and security.

[0004] As an individual characteristic of human beings, the human face is personal privacy data and is closely related to personal rights and interests. If facial information is leaked, it will cause great damage to the individual's information security. Therefore, how to prevent information leakage during the use of facial recognition and protect personal facial privacy information is a technical problem that needs to be urgently solved in identity authentication. Summary of the Invention

[0005] The present invention aims to at least solve the technical problems existing in the prior art. To this end, the present invention provides a secure face recognition method, system, device and storage medium that can prevent information leakage during face recognition and improve the security of private data.

[0006] A first aspect of the present invention provides a secure face recognition method for use with a comparison server, comprising the following steps:

[0007] Receiving a user ID, a ciphertext of user facial feature data, a ciphertext of facial features in a database, and a key index of a subject library from an authentication server, wherein the user ID and the ciphertext of user facial feature data are sent by a terminal to the authentication server, and the ciphertext of user facial feature data is obtained by encrypting the user facial feature data with a pre-stored user private key; the key index of the subject library and the ciphertext of facial features in the database are sent by the database to the authentication server, and the key index of the subject library and the ciphertext of facial features in the database correspond to the user ID;

[0008] Perform key matching according to the key index of the subject database to obtain the corresponding symmetric key;

[0009] Decrypting the facial feature ciphertext in the database according to the symmetric key to obtain the facial feature plaintext in the database;

[0010] Perform key matching based on the user ID to obtain the user public key corresponding to the user private key;

[0011] Decrypting the ciphertext of the user's facial feature data according to the user's public key to obtain the plaintext of the user's facial feature data;

[0012] Compare the user's facial feature data plaintext with the facial feature plaintext in the database to obtain a face recognition result.

[0013] The face recognition result is sent to the authentication server, so that the authentication server sends the face recognition result to the terminal according to the user ID.

[0014] The control method according to the embodiment of the present invention has at least the following beneficial effects:

[0015] This method receives a user ID, a ciphertext of user facial feature data, a ciphertext of facial feature in a database, and a key index of a subject library from an authentication server, wherein the key index of the subject library and the ciphertext of facial feature in the database correspond to the user ID; performs key matching according to the key index of the subject library to obtain a corresponding symmetric key; increases the security of private data through a one-to-one key pair, decrypts the ciphertext of facial feature in the database according to the symmetric key to obtain a plaintext of facial feature in the database; performs key matching according to the user ID to obtain a public key of the user corresponding to the private key of the user; decrypts the ciphertext of user facial feature data according to the user public key to obtain a plaintext of user facial feature data; compares the plaintext of user facial feature data with the plaintext of facial feature in the database to obtain a face recognition result, and sends the face recognition result to the authentication server, so that the authentication server sends the face recognition result to the terminal according to the user ID. By performing data decryption only when comparing facial feature data, the risk of information leakage during the use of face recognition is reduced, thereby improving the security of private data.

[0016] According to some embodiments of the present invention, before the database sends the facial feature ciphertext of the database to the authentication server, the process includes:

[0017] Receiving the user ID and the encrypted user registered face data from the authentication server, wherein the encrypted user registered face data is obtained by encrypting the user registered face data with a pre-stored user private key;

[0018] Perform key matching based on the user ID to obtain the user public key corresponding to the user private key;

[0019] Decrypting the user registered face data ciphertext according to the user public key to obtain the user registered face data plaintext, and extracting the user registered face feature data from the user registered face data plaintext;

[0020] Perform symmetrical encryption on the user's registered facial feature data through KMS according to the encryption index to obtain the facial feature ciphertext of the database;

[0021] The encrypted index, the user ID and the ciphertext of the facial features of the database are sent to the database, so that the database saves the encrypted index, the user ID and the ciphertext of the facial features of the database.

[0022] According to some embodiments of the present invention, the terminal obtains the encrypted user facial feature data in the following manner, including:

[0023] Receiving the user private key sent by the comparison server;

[0024] Collecting a user's facial image, and extracting the user's facial feature data from the user's facial image;

[0025] The user's facial feature data is encrypted using the user's private key to obtain a ciphertext of the user's facial feature data.

[0026] According to some embodiments of the present invention, the database obtains the subject library key index in the following manner, including:

[0027] Receiving a subject database key index acquisition request and the user ID sent by the authentication server;

[0028] The subject library key index is obtained according to the subject library key index obtaining request and the user ID.

[0029] According to some embodiments of the present invention, the database obtains the facial feature ciphertext of the database in the following manner, including:

[0030] receiving the user ID sent by the authentication server;

[0031] Data matching is performed according to the user ID to obtain the facial feature ciphertext of the database.

[0032] According to some embodiments of the present invention, performing key matching according to the subject library key index to obtain the corresponding symmetric key includes:

[0033] Key matching is performed according to the key index of the subject library, and the corresponding symmetric key is generated through KMS.

[0034] According to some embodiments of the present invention, before performing key matching according to the user ID to obtain a user public key corresponding to the user private key, the method further includes:

[0035] The user private key and the user public key corresponding to the user private key are generated through an asymmetric encryption algorithm.

[0036] A second aspect of the present invention provides a secure face recognition system for use with a comparison server, the secure face recognition system comprising:

[0037] A facial data acquisition module is configured to receive a user ID, a ciphertext of user facial feature data, a ciphertext of facial features in a database, and a key index of a subject library from an authentication server, wherein the user ID and the ciphertext of user facial feature data are sent by a terminal to the authentication server, and the ciphertext of user facial feature data is obtained by encrypting the user facial feature data with a pre-stored user private key; the key index of the subject library and the ciphertext of facial features in the database are sent by the database to the authentication server, and the key index of the subject library and the ciphertext of facial features in the database correspond to the user ID;

[0038] A symmetric key matching module, configured to perform key matching based on the key index of the subject library to obtain a corresponding symmetric key;

[0039] A database ciphertext decryption module, configured to decrypt the facial feature ciphertext in the database using the symmetric key to obtain the facial feature plaintext in the database;

[0040] A key matching module is used to perform key matching based on the user ID to obtain a user public key corresponding to the user private key;

[0041] A user data decryption module is used to decrypt the user facial feature data ciphertext according to the user public key to obtain the user facial feature data plaintext;

[0042] A face recognition module is used to compare the plaintext facial feature data of the user with the plaintext facial feature data in the database to obtain a face recognition result;

[0043] The result sending module is used to send the face recognition result to the authentication server, so that the authentication server sends the face recognition result to the terminal according to the user ID.

[0044] This system receives the user ID, the user's facial feature data ciphertext, the facial feature ciphertext of the database and the subject library key index from the authentication server, wherein the subject library key index and the facial feature ciphertext of the database correspond to the user ID; performs key matching according to the subject library key index to obtain the corresponding symmetric key; increases the security of private data through a one-to-one key pair, decrypts the facial feature ciphertext of the database according to the symmetric key to obtain the facial feature plaintext of the database; performs key matching according to the user ID to obtain the user's public key corresponding to the user's private key; decrypts the user's facial feature data ciphertext according to the user's public key to obtain the user's facial feature data plaintext; compares the user's facial feature data plaintext with the facial feature plaintext of the database to obtain the face recognition result, and sends the face recognition result to the authentication server, so that the authentication server sends the face recognition result to the terminal according to the user ID. By decrypting data only when comparing facial feature data, the risk of information leakage during the use of face recognition is reduced, and the security of private data is improved.

[0045] In a third aspect of the present invention, a secure face recognition electronic device is provided, comprising at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute the above-mentioned secure face recognition method.

[0046] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned secure face recognition method.

[0047] It should be noted that the beneficial effects between the second to fourth aspects of the present invention and the prior art are the same as the beneficial effects between the above-mentioned secure face recognition system and the prior art, and will not be described in detail here.

[0048] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments with reference to the following drawings, in which:

[0050] Figure 1 is a flow chart of a secure face recognition method according to an embodiment of the present invention;

[0051] Figure 2 This is a registration flow chart of a secure face recognition method provided by an embodiment of the present invention;

[0052] Figure 3 It is a structural diagram of a secure face recognition system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0054] In the description of the present invention, if there is a description of first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0055] In the description of the present invention, it should be understood that descriptions involving orientation, such as the orientation or positional relationship indicated by up, down, etc., are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0056] In the description of the present invention, it should be noted that, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0057] Facial recognition is primarily used for identity verification. It extracts biometric facial information from images or video streams and compares it with a facial feature database in real time, enabling rapid identification. Facial recognition technology is widely used in government, military, public security, finance, e-commerce, social management, public services, and security.

[0058] As an individual characteristic of human beings, the human face is personal privacy data and is closely related to personal rights and interests. If facial information is leaked, it will cause great damage to the individual's information security. Therefore, how to prevent information leakage during the use of facial recognition and protect personal facial privacy information is a technical problem that needs to be urgently solved in identity authentication.

[0059] In order to solve the above technical defects, refer to Figure 1 The present invention provides a secure face recognition method for comparing servers, comprising:

[0060] Step S101: Receive a user ID, ciphertext of user facial feature data, ciphertext of facial features in a database, and a key index of a subject library from an authentication server, wherein the user ID and ciphertext of user facial feature data are sent by the terminal to the authentication server, and the ciphertext of user facial feature data is obtained by encrypting the user facial feature data using a pre-stored user private key; the key index of the subject library and the ciphertext of facial features in the database are sent by the database to the authentication server, and the key index of the subject library and the ciphertext of facial features in the database correspond to the user ID;

[0061] Step S102: perform key matching according to the key index of the subject database to obtain the corresponding symmetric key;

[0062] Step S103: decrypt the facial feature ciphertext in the database using the symmetric key to obtain the facial feature plaintext in the database;

[0063] Step S104: Perform key matching based on the user ID to obtain the user public key corresponding to the user private key;

[0064] Step S105: decrypt the ciphertext of the user's facial feature data according to the user's public key to obtain the plaintext of the user's facial feature data;

[0065] Step S106: Compare the plaintext facial feature data of the user with the plaintext facial feature data in the database to obtain a facial recognition result;

[0066] Step S107: Send the face recognition result to the authentication server, so that the authentication server sends the face recognition result to the terminal according to the user ID.

[0067] This method receives a user ID, a ciphertext of user facial feature data, a ciphertext of facial feature in a database, and a key index of a subject library from an authentication server, wherein the key index of the subject library and the ciphertext of facial feature in the database correspond to the user ID; performs key matching according to the key index of the subject library to obtain a corresponding symmetric key; increases the security of private data through a one-to-one key pair, decrypts the ciphertext of facial feature in the database according to the symmetric key to obtain a plaintext of facial feature in the database; performs key matching according to the user ID to obtain a public key of the user corresponding to the private key of the user; decrypts the ciphertext of user facial feature data according to the user public key to obtain a plaintext of user facial feature data; compares the plaintext of user facial feature data with the plaintext of facial feature in the database to obtain a face recognition result, and sends the face recognition result to the authentication server, so that the authentication server sends the face recognition result to the terminal according to the user ID. By performing data decryption only when comparing facial feature data, the risk of information leakage during the use of face recognition is reduced, thereby improving the security of private data.

[0068] Specifically, in some embodiments, each piece of facial feature comparison ciphertext data is assigned a unique index, and the index also corresponds to a symmetric key.

[0069] Reference Figure 2 In some embodiments, before the database sends the facial feature ciphertext of the database to the authentication server, the following steps are included:

[0070] Step S201: Receive a user ID and a ciphertext of the user's registered face data from an authentication server, where the ciphertext of the user's registered face data is obtained by encrypting the user's registered face data with a pre-stored user private key;

[0071] Step S202: Perform key matching based on the user ID to obtain the user public key corresponding to the user private key;

[0072] Step S203: decrypt the ciphertext of the user's registered face data according to the user's public key to obtain the plaintext of the user's registered face data, and extract the user's registered face feature data from the plaintext of the user's registered face data;

[0073] Step S204: symmetrically encrypt the user's registered facial feature data through KMS according to the encryption index to obtain the facial feature ciphertext in the database;

[0074] Step S205: Send the encrypted index, user ID, and the ciphertext of the facial features in the database to the database, so that the database saves the encrypted index, user ID, and the ciphertext of the facial features in the database.

[0075] In some embodiments, the terminal obtains the encrypted user facial feature data in the following manner, including:

[0076] Receive the user private key sent by the comparison server;

[0077] Collecting user face images and extracting user face feature data from the user face images;

[0078] The user's facial feature data is encrypted using the user's private key to obtain the ciphertext of the user's facial feature data.

[0079] In some embodiments, the database obtains the subject library key index by:

[0080] Receive the subject database key index acquisition request and user ID sent by the authentication server;

[0081] Obtain the subject library key index based on the subject library key index acquisition request and user ID.

[0082] In some embodiments, the database obtains the facial feature ciphertext in the database by:

[0083] Receive the user ID sent by the authentication server;

[0084] Data matching is performed based on the user ID to obtain the facial feature ciphertext of the database.

[0085] In some embodiments, performing key matching based on the subject library key index to obtain the corresponding symmetric key includes:

[0086] Key matching is performed based on the key index of the subject database, and the corresponding symmetric key is generated through KMS.

[0087] In some embodiments, before performing key matching according to the user ID to obtain the user public key corresponding to the user private key, the method further includes:

[0088] Generate the user's private key and the user's public key corresponding to the user's private key through an asymmetric encryption algorithm.

[0089] Specifically, in some embodiments, the asymmetric cryptographic algorithm uses, for example, the international cryptographic algorithm standard RSA and the domestic cryptographic algorithm standard SM2. Furthermore, the facial feature database encrypts and stores the facial feature comparison data set using a symmetric cryptographic algorithm, such as the international cryptographic algorithm standard 3DES and the domestic cryptographic algorithm standard SM4.

[0090] This method can be set to provide a one-to-one comparison and identification service, or a one-to-many comparison and identification service.

[0091] The comparison server in this method includes a key management module, which manages symmetric and asymmetric cryptographic algorithm keys, including functions such as key creation, key disabling, key deletion, key import, and key allocation. The key management module connects to the cryptographic service module via a key management interface unit. The key management module provides the user's public key based on the user ID and the symmetric cryptographic algorithm key based on the index of the facial feature database.

[0092] In addition, refer to Figure 3 One embodiment of the present invention provides a secure face recognition system for use with a comparison server, comprising a face data acquisition module 1100, a symmetric key matching module 1200, a database ciphertext decryption module 1300, a key matching module 1400, a user data decryption module 1500, a face recognition module 1600, and a result sending module 1700, wherein:

[0093] The facial data acquisition module 1100 is used to receive a user ID, a ciphertext of the user's facial feature data, a ciphertext of the facial feature data in the database, and a key index of a thematic library from the authentication server. The user ID and the ciphertext of the user's facial feature data are sent by the terminal to the authentication server, and the ciphertext of the user's facial feature data is obtained by encrypting the user's facial feature data using a pre-stored user private key. The thematic library key index and the ciphertext of the facial feature data in the database are sent by the database to the authentication server, and the thematic library key index and the ciphertext of the facial feature data in the database correspond to the user ID.

[0094] The symmetric key matching module 1200 is used to perform key matching based on the key index of the subject library to obtain the corresponding symmetric key;

[0095] The database ciphertext decryption module 1300 is used to decrypt the facial feature ciphertext in the database according to the symmetric key to obtain the facial feature plaintext in the database;

[0096] The key matching module 1400 is used to perform key matching based on the user ID to obtain the user public key corresponding to the user private key;

[0097] The user data decryption module 1500 is used to decrypt the ciphertext of the user's facial feature data according to the user's public key to obtain the plaintext of the user's facial feature data;

[0098] The face recognition module 1600 is used to compare the user's facial feature plaintext data with the facial feature plaintext data in the database to obtain a face recognition result;

[0099] The result sending module 1700 is used to send the face recognition result to the authentication server, so that the authentication server sends the face recognition result to the terminal according to the user ID.

[0100] This system receives the user ID, the user's facial feature data ciphertext, the facial feature ciphertext of the database and the subject library key index from the authentication server, wherein the subject library key index and the facial feature ciphertext of the database correspond to the user ID; performs key matching according to the subject library key index to obtain the corresponding symmetric key; increases the security of private data through a one-to-one key pair, decrypts the facial feature ciphertext of the database according to the symmetric key to obtain the facial feature plaintext of the database; performs key matching according to the user ID to obtain the user's public key corresponding to the user's private key; decrypts the user's facial feature data ciphertext according to the user's public key to obtain the user's facial feature data plaintext; compares the user's facial feature data plaintext with the facial feature plaintext of the database to obtain the face recognition result, and sends the face recognition result to the authentication server, so that the authentication server sends the face recognition result to the terminal according to the user ID. By decrypting data only when comparing facial feature data, the risk of information leakage during the use of face recognition is reduced, and the security of private data is improved.

[0101] It should be noted that this system embodiment and the above-mentioned system embodiment are based on the same inventive concept, so the relevant content of the above-mentioned method embodiment is also applicable to this system embodiment and will not be repeated here.

[0102] The present application also provides a secure face recognition electronic device, comprising: a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, it implements: the secure face recognition method as described above.

[0103] The processor and the memory may be connected via a bus or other means.

[0104] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0105] The non-transient software program and instructions required to implement the secure face recognition method of the above embodiment are stored in the memory. When executed by the processor, the secure face recognition method of the above embodiment is executed, for example, the above described Figure 1 Method steps S101 to S107.

[0106] The present application also provides a computer-readable storage medium storing computer-executable instructions, which are used to execute: the secure face recognition method as described above.

[0107] The computer-readable storage medium stores computer-executable instructions, which are executed by a processor or controller, for example, by a processor in the above-mentioned electronic device embodiment, so that the above-mentioned processor can execute the secure face recognition method in the above-mentioned embodiment, for example, execute the above-mentioned Figure 1 Method steps S101 to S107.

[0108] Those skilled in the art will appreciate that all or some of the steps and systems in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program elements, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program elements, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0109] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments. Various changes can be made within the scope of knowledge possessed by ordinary technicians in the relevant technical field without departing from the scope of the present invention.

Claims

1. A secure face recognition method, characterized in that: For comparison servers, the secure face recognition method includes: Receive the user ID and the encrypted user's registered face data from the authentication server. The encrypted user's registered face data is obtained by encrypting the user's registered face data with the pre-stored user private key. Perform key matching based on the user ID to obtain the user public key corresponding to the user private key; Decrypting the user registered face data ciphertext according to the user public key to obtain the user registered face data plaintext, and extracting the user registered face feature data from the user registered face data plaintext; According to the encryption index, the user's registered facial feature data is symmetrically encrypted through KMS to obtain the facial feature ciphertext of the database; Sending the encrypted index, the user ID, and the ciphertext of the facial features in the database to the database, so that the database stores the encrypted index, the user ID, and the ciphertext of the facial features in the database; Receiving a user ID, a ciphertext of user facial feature data, a ciphertext of facial features in a database, and a key index of a subject library from an authentication server, wherein the user ID and the ciphertext of user facial feature data are sent by a terminal to the authentication server, and the ciphertext of user facial feature data is obtained by encrypting the user facial feature data with a pre-stored user private key; the key index of the subject library and the ciphertext of facial features in the database are sent by the database to the authentication server, and the key index of the subject library and the ciphertext of facial features in the database correspond to the user ID; Perform key matching according to the key index of the subject database to obtain the corresponding symmetric key; Decrypting the facial feature ciphertext in the database according to the symmetric key to obtain the facial feature plaintext in the database; Perform key matching based on the user ID to obtain the user public key corresponding to the user private key; Decrypting the ciphertext of the user's facial feature data according to the user's public key to obtain the plaintext of the user's facial feature data; Comparing the user's facial feature data plaintext with the facial feature plaintext in the database to obtain a facial recognition result; The face recognition result is sent to the authentication server, so that the authentication server sends the face recognition result to the terminal according to the user ID.

2. A secure face recognition method according to claim 1, characterized in that: The terminal obtains the encrypted user facial feature data in the following manner, including: Receiving the user private key sent by the comparison server; Collecting a user's facial image, and extracting the user's facial feature data from the user's facial image; The user's facial feature data is encrypted using the user's private key to obtain a ciphertext of the user's facial feature data.

3. A secure face recognition method according to claim 1, characterized in that: The database obtains the subject library key index in the following manner, including: Receiving a subject database key index acquisition request and the user ID sent by the authentication server; The subject library key index is obtained according to the subject library key index obtaining request and the user ID.

4. A secure face recognition method according to claim 1, characterized in that: The database obtains the facial feature ciphertext of the database in the following manner, including: receiving the user ID sent by the authentication server; Data matching is performed according to the user ID to obtain the facial feature ciphertext of the database.

5. A secure face recognition method according to claim 1, characterized in that: The performing key matching according to the subject database key index to obtain the corresponding symmetric key includes: Key matching is performed according to the key index of the subject library, and the corresponding symmetric key is generated through KMS.

6. A secure face recognition method according to claim 1, characterized in that: Before performing key matching according to the user ID to obtain a user public key corresponding to the user private key, the method further includes: The user private key and the user public key corresponding to the user private key are generated through an asymmetric encryption algorithm.

7. A secure face recognition system, characterized in that: For comparison with the server, the secure face recognition system includes: The face data acquisition module is used to receive the user ID and the user registered face data ciphertext from the authentication server, the user registered face data ciphertext is obtained by encrypting the user registered face data with the pre-stored user private key; perform key matching according to the user ID to obtain the user public key corresponding to the user private key; decrypt the user registered face data ciphertext according to the user public key to obtain the user registered face data plaintext, and extract the user registered face feature data from the user registered face data plaintext; perform feature data symmetrical encryption on the user registered face feature data through KMS according to the encryption index to obtain the face feature ciphertext of the database; combine the encryption index, the user ID and the face data of the database The facial feature ciphertext is sent to the database so that the database stores the encrypted index, the user ID and the facial feature ciphertext of the database; the user ID, the user facial feature data ciphertext, the facial feature ciphertext of the database and the subject library key index are received from the authentication server, wherein the user ID and the user facial feature data ciphertext are sent by the terminal to the authentication server, and the user facial feature data ciphertext is obtained by encrypting the user facial feature data with a pre-stored user private key; the subject library key index and the facial feature ciphertext of the database are sent by the database to the authentication server, and the subject library key index and the facial feature ciphertext of the database correspond to the user ID; A symmetric key matching module, configured to perform key matching based on the key index of the subject library to obtain a corresponding symmetric key; A database ciphertext decryption module, configured to decrypt the facial feature ciphertext in the database using the symmetric key to obtain the facial feature plaintext in the database; A key matching module is used to perform key matching based on the user ID to obtain a user public key corresponding to the user private key; A user data decryption module is used to decrypt the user facial feature data ciphertext according to the user public key to obtain the user facial feature data plaintext; A face recognition module is used to compare the plaintext facial feature data of the user with the plaintext facial feature data in the database to obtain a face recognition result; The result sending module is used to send the face recognition result to the authentication server, so that the authentication server sends the face recognition result to the terminal according to the user ID.

8. A secure face recognition device, characterized in that: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute a secure face recognition method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute a secure face recognition method according to any one of claims 1 to 6.

Images