Identity verification method and related equipment
Through multi-party security computing technology, the matching of user identification and biological information is solved, and the problem of user privacy information exposure is achieved, the security and privacy protection of identity verification is achieved, and the economic losses and data leakage risks are reduced.
Patent Information
- Application Number
- CN202411031454.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-19
AI Technical Summary
In the existing identity verification methods, the risk of user privacy information exposure leads to commercial secret leakage and economic losses, and cannot effectively protect the user's privacy information in the database.
Multi-party security computing technology is adopted to cooperate between the identity verification party and the identity information storage party, and multi-party security computing is used to match the target user identity and biological information to ensure that the matching results do not expose data, and identity verification is only performed based on the matching results.
Identity verification is completed without leaking user data, protecting user privacy and merchant information, avoiding competitors from obtaining user lists, reducing economic losses, and maintaining the privacy and security of database users.
Smart Images

Figure CN118984227A_ABST
Abstract
Description
Technical Field
[0001] One or more embodiments of the present specification relate to the field of secure computing technology, and more particularly, to an identity verification method and related equipment. Background Art
[0002] In order to prevent fraud or meet relevant regulatory requirements, merchants or platforms need to verify the identity of registered users. Generally, merchants or platforms often send the user identification (such as ID card) and biometric information (such as face) filled in by the registered user to the database, which will compare the user identification and biometric information of the registered user with a large number of user identifications and biometric information stored in the database to verify whether the user identification and biometric information filled in by the registered user are authentic and match.
[0003] However, since during the above-mentioned identity verification process, the merchant or platform needs to send the registered user's user ID and biometric information to the database, there is a risk of user privacy information being exposed, which may in turn leak the merchant or platform's user list to competitors, leading to serious economic losses caused by the leakage of business secrets. Summary of the invention
[0004] In view of this, one or more embodiments of this specification provide an identity verification method and related devices.
[0005] In a first aspect, this specification provides an identity verification method, which is applied to a first service device corresponding to an identity verification party, and a database of a second service device corresponding to an identity information storage party maintains identity information of multiple users, wherein the identity information includes a user identifier and user biometric information; the method includes:
[0006] Obtaining a target user identifier and target user biometric information corresponding to the target user to be verified;
[0007] performing multi-party secure computation on the target user identifier and multiple user identifiers in the database to determine whether the target user identifier matches the multiple user identifiers; and,
[0008] Performing multi-party secure computing on the target user biometric information and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information;
[0009] The identity of the target user is verified according to the matching result of the target user identification and the matching result of the target user biometric information.
[0010] In a second aspect, the present specification provides an identity verification device, which is applied to a first service device corresponding to an identity verification party, and a database of a second service device corresponding to an identity information storage party maintains identity information of multiple users, wherein the identity information includes a user identifier and user biometric information; the device includes:
[0011] An acquisition unit, used to acquire a target user identification and target user biometric information corresponding to the target user to be verified;
[0012] A user identification matching unit is used to perform multi-party security calculation on the target user identification and multiple user identifications in the database to determine whether the target user identification matches the multiple user identifications; and
[0013] A user biometric information matching unit, configured to perform multi-party secure computing on the target user biometric information and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information;
[0014] The identity verification unit is used to verify the identity of the target user according to the matching result of the target user identification and the matching result of the target user biometric information.
[0015] Accordingly, this specification also provides a computing device, comprising: a memory and a processor; the memory stores computer programs / instructions that can be executed by the processor; when the processor executes the computer program / instructions, it executes the identity verification method described in the first aspect above.
[0016] Accordingly, the present specification also provides a computer-readable storage medium on which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, the identity verification method as described in the first aspect above is executed.
[0017] Accordingly, the present specification also provides a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, the identity verification method described in the first aspect above is performed.
[0018] In summary, the present application can be applied to the first service device corresponding to the identity verification party, and the database of the second service device corresponding to the identity information storage party can maintain the identity information of multiple users, and the identity information may include a user identifier and user biometric information. In one illustrated embodiment, the first service device can first obtain the target user identifier and target user biometric information corresponding to the target user to be verified. Then, the first service device of the identity verification party can jointly with the second service device of the identity information storage party perform multi-party security calculation on the above-mentioned target user identifier and multiple user identifiers in the database to determine whether the target user identifier matches the multiple user identifiers in the database; and perform multi-party security calculation on the above-mentioned target user biometric information and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information in the database. Furthermore, the first service device of the identity verification party can verify the identity of the above-mentioned target user based on the matching result of the target user identifier and the matching result of the target user biometric information. In this way, this application can determine whether the target user identification and target user biometric information of the target user to be verified match the user identification and user biometric information already in the database without exposing the data of each party through multi-party secure computing, so as to complete the identity verification of the target user. It not only effectively protects the identity information of the target user held by the identity verification party from being leaked, and avoids competitors knowing their user lists, thereby causing economic losses to the identity verification party, but also protects the privacy security of a large number of users maintained in the database. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 is a schematic diagram of a system architecture provided by an exemplary embodiment;
[0020] Figure 2 is a flowchart of an identity verification method provided by an exemplary embodiment;
[0021] Figure 3 is a flowchart of another identity verification method provided by an exemplary embodiment;
[0022] Figure 4 is a schematic structural diagram of an identity verification device provided by an exemplary embodiment;
[0023] Figure 5 It is a structural diagram of a computing device provided by an exemplary embodiment. DETAILED DESCRIPTION
[0024] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of this specification. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.
[0025] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may be combined into a single step for description in other embodiments.
[0026] In addition, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0027] First, some terms in this specification are explained to facilitate understanding by those skilled in the art.
[0028] (1) Secure Multi-Party Computation (SMPC), also known as secure multi-party computing, is used to solve the problem of privacy-preserving collaborative computing between a group of mutually distrusting parties. SMPC can ensure the independence of data input and the correctness of data calculation, while not leaking the input data of each party to other parties participating in the calculation.
[0029] (2) Secret Sharing (SS) is a commonly used security protocol in multi-party secure computing. In the process of multi-party secure computing, in order to prevent the disclosure of data of each party and intermediate computing results, the computing is usually kept in a shared state. Secret sharing splits the secret information (such as data of each party and intermediate computing results) in an appropriate manner and assigns each split to different participants for management. Each participant cannot recover the secret information alone, and only when several participants work together can the secret information be recovered.
[0030] As mentioned above, in order to prevent fraud or meet relevant regulatory requirements, merchants or platforms need to verify the identity of registered users. Generally, merchants or platforms often send the user identification (such as ID card or mobile phone number, etc.) and biometric information (such as fingerprint or face, etc.) filled in by the registered user to the database, and the database will compare the user identification and user biometric information of the registered user with a large number of user identifications and a large amount of biometric information stored in the database to verify whether the user identification and user biometric information filled in by the registered user are authentic and whether they match.
[0031] However, since during the above-mentioned identity verification process, the merchant or platform needs to send the user ID and biometric information filled in by the registered user to the database, there is a risk of user privacy information being exposed, which may in turn leak the merchant or platform's user list to competitors, resulting in serious economic losses caused by the leakage of business secrets.
[0032] Based on this, this specification provides a technical solution that can determine whether the target user identification and target user biometric information to be verified match the user identification and user biometric information already in the database through multi-party secure computing without exposing the data of each party, so as to complete the identity verification of the user.
[0033] In implementation, the present application can be applied to the first service device corresponding to the identity verification party, and the database of the second service device corresponding to the identity information storage party can maintain the identity information of multiple users, and the identity information can include user identification and user biometric information. In one illustrated embodiment, the first service device can first obtain the target user identification and target user biometric information corresponding to the target user to be verified. Then, the first service device of the identity verification party can jointly with the second service device of the identity information storage party perform multi-party security calculation on the above-mentioned target user identification and multiple user identifications in the database to determine whether the target user identification matches the multiple user identifications in the database; and perform multi-party security calculation on the above-mentioned target user biometric information and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information in the database. Furthermore, the first service device of the identity verification party can verify the identity of the above-mentioned target user based on the matching result of the target user identification and the matching result of the target user biometric information.
[0034] In the above technical solution, this application can determine whether the target user identification and target user biometric information of the target user to be verified match the user identification and user biometric information already in the database without exposing the data of each party through multi-party secure computing, so as to complete the identity verification of the target user. In this way, the identity information of the target user held by the identity verification party is effectively protected from being leaked, and competitors are prevented from knowing their user lists, thereby causing economic losses to the identity verification party. At the same time, the privacy information security of a large number of users maintained in the database is also protected.
[0035] See also Figure 1 , Figure 1 FIG. 1 is a schematic diagram of a system architecture provided by an exemplary embodiment. Figure 1 As shown, one or more embodiments provided in this specification may be Figure 1 The present invention is specifically implemented in the system architecture shown or a similar system architecture.
[0036] like Figure 1 As shown, the system includes a service device 100 and a service device 200, wherein the service device 100 may be a service device corresponding to the identity verification party, and the service device 200 may be a service device corresponding to the identity information storage party. In an embodiment shown, a communication connection may be established between the service device 100 and the service device 200 in any possible manner, and this specification does not specifically limit this.
[0037] like Figure 1 As shown, the service device 200 may be equipped with a database corresponding to the identity information storage party, and the identity information of multiple users is maintained in the database. Exemplarily, the identity information of the user may include but is not limited to the user identification and user biometric information. In an embodiment shown, the identity information storage party may be some official data management platform, which is not specifically limited in this specification.
[0038] It should be noted that this specification does not specifically limit the specific content of the user identification and user biometric information.
[0039] Exemplarily, the user identification may include, but is not limited to, one or more combinations of the following: the user's application account, the user's mobile phone number, the user's ID card, and the like.
[0040] Exemplarily, the user's biometric information may include, but is not limited to, one or more combinations of the following: a user's fingerprint, a user's palm print, a user's iris, a user's face, and the like.
[0041] In an illustrated implementation, the service device 100 may first obtain a target user identification and target user biometric information of a target user to be verified.
[0042] It should be noted that this specification does not specifically limit the specific implementation method in which the service device 100 obtains the target user identification and target user biometric information of the target user to be verified.
[0043] Exemplarily, the service device 100 can be used as a server device of the target application, and the target application can be run in the client device (not shown in the figure) connected to it. The target user can enter his or her target user identification and target user biometric information in the user registration interface of the target application through the client device, and accordingly, the client device can obtain the target user identification and target user biometric information entered by the target user. Further, the client device can send the obtained target user identification and target user biometric information to the service device 100 connected to it, so that the service device 100 can obtain the target user identification and target user biometric information of the target user to be verified.
[0044] In one illustrated embodiment, the target application may be any type of application that requires verification of user identity when registering, such as a financial management application, a communication application, a game application, etc., and this specification does not specifically limit this.
[0045] Furthermore, the service device 100 may verify the identity of the target user based on the acquired target user identifier and target user biometric information.
[0046] In an illustrated embodiment, the service device 100 may jointly with the service device 200 of the identity information storage party perform multi-party security computation on the target user identifier to be verified and multiple user identifiers in the database to determine whether the target user identifier matches the multiple user identifiers in the database.
[0047] Similarly, the service device 100 can also cooperate with the service device 200 of the identity information storage party to perform multi-party security computing on the above-mentioned target user biometric information to be verified and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information in the database.
[0048] It should be understood that when performing multi-party secure computing, the target user identifier participating in the computing, multiple user identifiers in the database, target user biometric information, and multiple user biometric information in the database are all confidential data. Figure 2 The description of the corresponding embodiments will not be repeated here.
[0049] In an illustrated embodiment, the multi-party secure computation for the target user identification and the multi-party secure computation for the target user biometric information may be performed simultaneously, thereby improving the efficiency and performance of identity verification.
[0050] Furthermore, the service device 100 can verify the identity of the target user based on the matching result of the target user identification and the matching result of the target user biometric information obtained by the multi-party secure computing. Figure 2 and Figure 3 The description of the corresponding embodiments will not be repeated here.
[0051] In one illustrated implementation, the service device 100 and the service device 200 may be a laptop computer, a desktop computer, a server, or a server cluster consisting of multiple servers, etc., which has the above functions, and this specification does not make any specific limitation on this.
[0052] See also Figure 2 , Figure 2 is a flowchart of an identity verification method provided by an exemplary embodiment. The method can be applied to Figure 1 The system architecture shown in FIG. 1 can be specifically applied to the service device 100 corresponding to the identity verification party in the system architecture. Figure 2 As shown, the identity verification method may specifically include the following steps S201 to S204.
[0053] Step S201, the first service device corresponding to the identity verification party obtains the target user identifier and target user biometric information corresponding to the target user to be verified; the database of the second service device corresponding to the identity information storage party maintains the identity information of multiple users, and the identity information includes user identifiers and user biometric information.
[0054] In an illustrated embodiment, a first service device (eg Figure 1 The service device 100 in the system architecture shown in the figure can first obtain the target user identification and target user biometric information corresponding to the target user to be verified. The specific implementation method can refer to the above Figure 1 The description of the corresponding embodiments will not be repeated here.
[0055] In addition, the database of the second service device corresponding to the identity information storage party maintains the identity information of multiple users, and the identity information may include but is not limited to user identification and user biometric information.
[0056] In an illustrated implementation, the database may maintain identity information of multiple users in the form of a data table, and each row of data records in the data table may be used to store the identity information of any user, which is not specifically limited in this specification.
[0057] Step S202: performing multi-party secure computation on the target user identifier and multiple user identifiers in the database to determine whether the target user identifier matches the multiple user identifiers.
[0058] Furthermore, the first service device may cooperate with the second service device of the identity information storage party to perform multi-party security computation on the target user identifier to be verified and multiple user identifiers in the database to determine whether the target user identifier matches the multiple user identifiers in the database.
[0059] It should be understood that the user identifier is generally an application account, ID card or mobile phone number. Based on this, an accurate match is usually required for the user identifier, that is, only when two user identifiers are completely equal can they be determined to match. If there is any difference between the two user identifiers, they cannot be matched.
[0060] It should be noted that this specification does not specifically limit the specific implementation method of how to determine whether the target user identifier matches multiple user identifiers in the database through multi-party secure computing.
[0061] In an illustrated embodiment, the first service device and the second service device may run a secure equality determination algorithm to perform multi-party secure computation on a target user identifier and multiple user identifiers in a database to determine whether the target user identifier is equal to each of the multiple user identifiers in the database.
[0062] In an illustrated embodiment, if, based on the above-mentioned secure equality determination algorithm, it is determined that the target user identifier is equal to any user identifier among the multiple user identifiers in the database, then it is determined that the target user identifier matches successfully; otherwise, if it is determined that the target user identifier is not equal to each user identifier among the multiple user identifiers, then it is determined that the target user identifier matches unsuccessfully.
[0063] It should be noted that this specification does not specifically limit the specific type of the security equality determination algorithm. In an illustrated embodiment, the above-mentioned security equality determination algorithm may include a security equality determination algorithm based on secret sharing. Exemplarily, the following will take the security equality determination algorithm based on secret sharing as an example to describe the matching process of the above-mentioned target user identifier.
[0064] First, the first service device uses secret sharing technology to split the target user identifier a it holds into two fragments, namely a1 and a2. The first service device retains a1 and sends a2 to the second service device.
[0065] Similarly, the second service device uses secret sharing technology to split one of the user identifiers b among the multiple user identifiers it holds into two fragments, namely b1 and b2. The second service device retains b1 and sends b2 to the first service device.
[0066] Then, the first service device generates a random number rA, and the second service device generates a random number rB. At this point, the first service device holds the fragment a1 of the target user identity a, the fragment b2 of the user identity b, and the random number rA, and the second service device holds the fragment a2 of the target user identity a, the fragment b1 of the user identity b, and the random number rB. In addition, the first service device can share the generated random number rA with the second service device, and the second service device can share the generated random number rB with the first service device.
[0067] Further, the first service device calculates cA=a1+rA-b2, and the second service device calculates cB=b1+rB-a2.
[0068] It is not difficult to understand that if a=b, that is, a1+a2=b1+b2, then a1-b2=b1-a2, and thus cA+cB=rA+rB, and correspondingly, if a≠b, then cA+cB≠rA+rB. Based on this, the first service device and the second service device can verify whether cA+cB is equal to a known public value (i.e., rA+rB) through an open, harmless protocol (such as additive homomorphic encryption or obfuscation circuit), thereby determining whether the target user identifier a and the user identifier b in the database are equal, and the actual values of a and b will not be disclosed, thereby protecting their respective privacy.
[0069] Other user identifiers in the database except the user identifier b can refer to the above steps and perform security equality determination with the target user identifier to determine whether the target user identifier is equal to each of the multiple user identifiers in the database.
[0070] In an illustrated implementation, the above-mentioned secure equal determination algorithm may also be a secure equal determination algorithm based on an obfuscation circuit, etc., which is not specifically limited in this specification. Exemplarily, the following will take the secure equal determination algorithm based on an obfuscation circuit as an example to describe the matching process of the above-mentioned target user identification.
[0071] First, the first service device can construct a Boolean logic circuit for comparing whether two input data (such as the target user identifier a and the user identifier b in the database) are equal. The circuit may include several gates, such as an exclusive OR gate (XOR), etc. Further, the first service device can run an obfuscation algorithm to confuse the constructed circuit to obtain a corresponding obfuscated circuit. Further, the first service device can send the obfuscated circuit and the label of the target user identifier a (i.e., the obfuscated value) to the second service device, and the second service device executes the obfuscated circuit based on the label of the target user identifier a and the label of the user identifier b, and sends the obfuscated result finally output by the obfuscated circuit to the first service device, and the first service device restores the obfuscated result to the actual value, thereby obtaining a determination result of whether the target user identifier a is equal to the user identifier b, etc. This specification does not make specific limitations on this.
[0072] In an illustrated embodiment, in addition to the above-mentioned secure equality determination algorithm, the first service device and the second service device may also run a private set intersection algorithm (PSI) to perform multi-party secure calculations on the target user identifier and multiple user identifiers in the database to determine whether the target user identifier is equal to each of the multiple user identifiers in the database.
[0073] Among them, PSI is a cryptographic protocol that allows two or more participants to find the common elements of their data sets without revealing other non-intersecting elements in the sets. This means that the participants can find the intersection of their data while protecting the contents of their respective sets from being known by the other party and any potential third party.
[0074] In one illustrated embodiment, the target user identifier can be taken as a set through a privacy intersection algorithm, and a privacy intersection is performed on it with a set consisting of multiple user identifiers in the database. If the calculated intersection is the target user identifier, it is determined that the target user identifier matches successfully; otherwise, if the calculated result is an empty set, it is determined that the target user identifier matches unsuccessfully.
[0075] It should be noted that this specification does not specifically limit the specific type of the privacy intersection algorithm. In an embodiment shown, the privacy intersection algorithm can be a privacy intersection algorithm based on the key exchange protocol in Elliptic Curve Diffie-Hellman (ECDH), or a privacy intersection algorithm based on an oblivious pseudo-random function (OPRF), etc. This specification does not specifically limit this.
[0076] Step S203: performing multi-party secure computing on the target user biometric information and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information.
[0077] In one illustrated embodiment, the first service device may also cooperate with the second service device of the identity information storage party to perform multi-party secure computing on the target user biometric information to be verified and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information in the database.
[0078] It should be understood that user biometric information generally includes a vector representing the user's biometric features, such as a vector representing the user's fingerprint features, or a vector representing the user's facial features. Based on this, fuzzy matching is usually required for user biometric information, that is, as long as the vector similarity of two user biometric information is greater than a preset threshold, it can be determined that the two match. If the vector similarity of two user biometric information is less than the preset threshold, they cannot match.
[0079] It should be noted that this specification does not specifically limit the specific implementation method of how to determine whether the target user's biometric information matches multiple user biometric information in the database through multi-party secure computing.
[0080] In one illustrated embodiment, the first service device and the second service device can run a vector similarity algorithm based on secret sharing to perform multi-party secure calculations on the target user's biometric information and multiple user biometric information in the database to obtain the vector similarity between the target user's biometric information and each user's biometric information in the multiple user biometric information in the database.
[0081] In an illustrated embodiment, if the vector similarity between the target user's biometric information and any user's biometric information in the database of multiple user's biometric information is greater than a preset threshold, it can be determined that the target user's biometric information matches successfully; otherwise, if the vector similarity between the target user's biometric information and each user's biometric information in the database of multiple user's biometric information is less than the preset threshold, it can be determined that the target user's biometric information matches unsuccessfully.
[0082] Alternatively, in some possible implementations, the target user's biometric information may have a vector similarity greater than a preset threshold with at least two of the multiple user biometric information in the database. In this case, it can also be considered that the target user's biometric information is risky, and thus it can be determined that the target user's biometric information has failed to match.
[0083] It should be noted that the present specification does not specifically limit the specific type of the vector similarity algorithm. In an illustrated embodiment, the vector similarity algorithm may include a cosine similarity algorithm or a Hamming similarity algorithm.
[0084] Among them, the cosine similarity algorithm or the Hamming similarity algorithm essentially calculates the inner product of two vectors and uses the inner product as the vector similarity. Judging whether the inner product is greater than a preset threshold is essentially a comparison operation. Therefore, conventional vector inner product operations and secure comparison operations based on secret sharing can be used to implement the above-mentioned vector similarity calculation and matching judgment.
[0085] In an illustrated embodiment, the above steps S202 and S203 can be performed in parallel, that is, the matching of the user identification and the matching of the user biometric information can be performed at the same time, thereby improving the efficiency of identity verification. In addition, the multi-party secure computation in the above steps S202 and S203 can also be implemented by any other possible method (such as obfuscated circuits or homomorphic encryption technologies), which is not specifically limited in this specification.
[0086] Step S204: verify the identity of the target user according to the matching result of the target user identification and the matching result of the target user biometric information.
[0087] Furthermore, the first service device may verify the identity of the target user according to the matching result of the target user identification and the matching result of the target user biometric information, obtain a corresponding identity verification result, and take corresponding measures for the target user according to the identity verification result.
[0088] In one illustrated embodiment, see Figure 3 , Figure 3 FIG. 1 is a flow chart of another identity verification method provided by an exemplary embodiment. Figure 3 As shown, this method can be applied to Figure 1 The system architecture shown in FIG. 1 can be specifically applied to the service device 100 corresponding to the identity verification party in the system architecture. Figure 3 As shown, the identity verification method may specifically include the following steps S301 to S304b-2.
[0089] Step S301: obtaining a target user identifier and target user biometric information corresponding to the target user to be verified.
[0090] In an embodiment shown, step S301 may be specifically referred to above. Figure 2 The description of step S201 in the corresponding embodiment is omitted here.
[0091] Step S302, performing multi-party security calculation on the target user identifier and multiple user identifiers in the database to determine whether the target user identifier matches the multiple user identifiers; and performing multi-party security calculation on the target user biometric information and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information.
[0092] In an embodiment shown, step S302 may be specifically referred to above. Figure 2 Step S202 and step S203 in the corresponding embodiment are described in detail and will not be repeated here.
[0093] like Figure 3 As shown, the present application may choose to expose the intermediate matching result to perform identity verification, that is, the matching result of the target user identification and the matching result of the target user biometric information may be a plain text matching result.
[0094] In an illustrated embodiment, the database further maintains multiple serial numbers corresponding to multiple user identifiers and multiple user biometric information, that is, each user identifier corresponds to a serial number, and each user biometric information also corresponds to a serial number; wherein the serial numbers corresponding to the user identifier and user biometric information of the same user are the same. Exemplarily, the database maintains a data record corresponding to each user in the form of a data table, and the data record may include a series of data such as the user identifier and user biometric information of the user, and each data record may correspond to a serial number.
[0095] Correspondingly, if the target user identifier matches successfully, the matching result obtained by the first service device may include the serial number of the user identifier in the database that matches the target user identifier; otherwise, if the target user identifier matches unsuccessfully, the matching result obtained by the first service device may not include any serial number.
[0096] Similarly, if the target user's biometric information matches successfully, the matching result obtained by the first service device may include the serial number of the user's biometric information in the database that matches the target user's biometric information; otherwise, if the target user's biometric information matches unsuccessfully, the matching result obtained by the first service device may not include any serial number, or may include the serial numbers of at least two user's biometric information that match the target user's biometric information.
[0097] It should be understood that the serial number of the user identification and the serial number of the user biometric information are both plain text serial numbers. In an illustrated embodiment, the plain text matching result (ie, the plain text serial number) can be exposed only to the first service device, and the second service device does not need to obtain the plain text matching result.
[0098] Step S303a, determining whether the target user identification and the target user biometric information are both successfully matched according to the matching result.
[0099] In an illustrated embodiment, the first service device may first determine whether the target user identifier and the target user biometric information are matched successfully according to the matching result. Exemplarily, if the matching result of the target user identifier obtained by the first service device includes a sequence number, it can be determined that the target user identifier is matched successfully, and if the matching result of the target user biometric information obtained by the first service device includes a sequence number, it can be determined that the target user biometric information is matched successfully.
[0100] like Figure 3 As shown, if at least one of the target user identification and the target user biometric information fails to match, it can be determined that the identity verification of the target user has failed.
[0101] like Figure 3 As shown, if the target user identification and the target user biometric information are matched successfully, step S304a can be further performed.
[0102] Step S304a: Check whether the serial number included in the matching result of the target user identification is consistent with the serial number included in the matching result of the target user biometric information.
[0103] Furthermore, if the target user identifier and the target user biometric information are both matched successfully, the first service device can further determine whether the serial number included in the matching result of the target user identifier is consistent with the serial number included in the matching result of the target user biometric information, that is, determine whether the user identifier and the user biometric information correspond to the same user.
[0104] like Figure 3 As shown, if the serial numbers in the two matching results are inconsistent, it can be determined that the identity verification of the target user has failed.
[0105] like Figure 3 As shown, if the serial numbers in the two matching results are consistent, it can be determined that the identity verification of the target user has passed.
[0106] As mentioned above, by directly comparing whether the plaintext serial numbers are consistent, the identity of the target user can be verified more quickly and easily, which greatly reduces the amount of computational complexity of secret state calculations and improves the efficiency of identity verification.
[0107] In addition, if Figure 3 As shown, the present application may also choose to perform identity verification in a manner that does not expose the intermediate matching results, that is, the matching result of the target user identification and the matching result of the target user biometric information are the ciphertext matching results.
[0108] In an illustrated embodiment, the matching result of the target user identification may include a first encrypted state vector.
[0109] Among them, the first secret state vector may include multiple elements corresponding to the matching results between the target user identifier and multiple user identifiers in the database; wherein the value of an element is 0, which may indicate that the user identifier corresponding to the element does not match the target user identifier, and the value of the element is 1, which may indicate that the user identifier corresponding to the element matches the target user identifier.
[0110] In an illustrated embodiment, the matching result of the target user's biometric information may include a second dense state vector.
[0111] Among them, the second secret state vector may include multiple elements corresponding to the matching results between the target user's biometric information and multiple user biometric information in the database; wherein the value of an element is 0, which may indicate that the user biometric information corresponding to the element does not match the target user's biometric information, and the value of the element is 1, which may indicate that the user biometric information corresponding to the element matches the target user's biometric information.
[0112] In an illustrated embodiment, after executing step S302, the first service device and the second service device can both obtain the above-mentioned first secret state vector and the second secret state vector. Exemplarily, the first secret state vector held by the first service device and the first secret state vector held by the second service device can be a shard of secret sharing, and only by combining the two first secret state vectors can the plaintext matching result vector of the target user identifier be restored, and the second secret state vector is the same. Exemplarily, the first secret state vector held by the first service device and the first secret state vector held by the second service device can also be a homomorphically encrypted ciphertext, and the second secret state vector is the same, and this specification does not make specific limitations on this.
[0113] Step S303b-1, securely multiply each element in the first secret state vector with the element at the corresponding position in the second secret state vector to obtain a multiplication result vector.
[0114] In an illustrated embodiment, the first service device and the second service device can perform a secure multiplication calculation on the first secret state vector and the second secret state vector. Specifically, the first service device and the second service device can perform a secure multiplication calculation on each element in the first secret state vector and the element at the corresponding position in the second secret state vector, and the first service device can obtain a multiplication result vector.
[0115] Exemplarily, the first secret state vector includes N elements, and the second secret state vector includes N elements, and the so-called secure multiplication calculation is to multiply the i-th element of the first secret state vector by the i-th element of the second secret state vector to obtain a multiplication result vector. Wherein, N is an integer greater than 1, and i is 1, 2, 3, ..., N in sequence.
[0116] It is not difficult to understand that only when the i-th element of the first dense state vector and the i-th element of the second dense state vector are both 1, the result of the multiplication of the two is 1, otherwise it is 0.
[0117] It should be noted that this specification does not specifically limit the specific implementation method of the secure multiplication calculation of the first secret state vector and the second secret state vector. In an illustrated embodiment, any possible method such as secret sharing or homomorphic encryption can be used to implement the secure multiplication calculation of the two secret state vectors.
[0118] Step S304b-1, determining whether there is only one element whose value is 1 among the multiple elements included in the multiplication result vector.
[0119] Furthermore, the first service device may count the number of elements whose value is 1 in the obtained multiplication result vector, and verify the identity of the target user according to the statistical result.
[0120] Specifically, the first service device may determine whether there is an element whose value is 1 among multiple elements included in the multiplication result vector.
[0121] In an illustrated embodiment, if there is an element whose value is 1 among the multiple elements contained in the multiplication result vector, it indicates that the target user identification and the target user biometric information are successfully matched and both correspond to the same user, and it can be determined that the identity verification of the target user is successful.
[0122] In an illustrated embodiment, if the values of multiple elements contained in the multiplication result vector are all 0, it indicates that at least one of the target user identifier and the target user biometric information fails to match, or the target user identifier and the target user biometric information both match successfully, but the two correspond to different users, and it can be determined that the identity verification of the target user fails.
[0123] Step S303b-2, performing a secure XOR calculation on each element in the first secret state vector and the element at the corresponding position in the second secret state vector to obtain an XOR result vector.
[0124] In an illustrated embodiment, the first service device and the second service device may perform a secure XOR calculation on the first secret state vector and the second secret state vector. Specifically, the first service device and the second service device may perform a secure XOR calculation on each element in the first secret state vector and the element at the corresponding position in the second secret state vector, and the first service device may obtain an XOR result vector.
[0125] For example, still taking the first secret state vector including N elements and the second secret state vector including N elements as an example, the so-called secure XOR calculation is to XOR the i-th element of the first secret state vector with the i-th element of the second secret state vector, thereby obtaining an XOR result vector. Similarly, N is an integer greater than 1, and i takes values of 1, 2, 3, ..., N in sequence.
[0126] It is not difficult to understand that if the i-th element of the first dense state vector and the i-th element of the second dense state vector have different values, that is, one of the elements has a value of 0 and the other has a value of 1, then the result of the XOR of the two will be 1, otherwise it will be 0.
[0127] It should be noted that this specification does not specifically limit the specific implementation method of the secure XOR calculation of the first secret state vector and the second secret state vector. In an illustrated embodiment, any possible method such as secret sharing or homomorphic encryption can be used to implement the secure XOR calculation of the two secret state vectors.
[0128] Step S304b-2, determining whether there is at least one element whose value is 1 among the multiple elements included in the XOR result vector.
[0129] Furthermore, the first service device may count the number of elements whose value is 1 in the obtained XOR result vector, and perform identity verification on the target user according to the statistical result.
[0130] Specifically, the first service device may determine whether there is at least one element whose value is 1 among multiple elements included in the XOR result vector.
[0131] In an illustrated embodiment, if at least one element among the multiple elements contained in the XOR result vector has a value of 1, it indicates that at least one of the target user identifier and the target user biometric information fails to match, or it indicates that both the target user identifier and the target user biometric information match successfully, but the two correspond to different users, and it can be determined that the identity verification of the target user fails.
[0132] In an illustrated embodiment, if multiple elements contained in the XOR result vector are all 0, it indicates that both the target user identifier and the target user biometric information have failed to match, and it can be determined that the identity verification of the target user has failed; or, it may also indicate that both the target user identifier and the target user biometric information have successfully matched, and the two correspond to the same user, and it can be determined that the identity verification of the target user has passed.
[0133] As described above, through secure calculation between the matching results of the ciphertext (i.e., the first secret state vector and the second secret state vector), the identity of the target user can be verified without leaking any data of both parties. The second service device does not even need to leak the serial number corresponding to the user identifier and user biometric information in the database to the first service device, thereby more comprehensively protecting the privacy and security of both parties.
[0134] In summary, the first service device verifies the identity of the target user based on the plaintext matching result (serial number) or the ciphertext matching result (encrypted state vector), and after obtaining the corresponding identity verification result, the corresponding operation can be performed on the target user based on the identity verification result. Exemplarily, if the identity verification of the target user passes, the target user can be allowed to complete the registration, log in to the target application through the registered account, and use a series of functions provided by the target application. Exemplarily, if the identity verification of the target user fails, the target user can be prompted that the registration failed and that the correct user identification and / or biometric information must be provided, etc. This specification does not specifically limit this.
[0135] In addition, in some possible implementations, the purpose of identity verification by the identity verification party may be only to confirm whether the target user biometric information provided by the target user is correct, or only to confirm whether the target user identifier provided by the target user is correct, or to confirm whether there is a situation where the target user identifier is correct but the target user biometric information is incorrect, or to confirm whether there is a situation where the target user biometric information is correct but the target user identifier is incorrect, etc. Based on this, the first service device may include multiple situations when authenticating the target user according to the matching result.
[0136] Exemplarily, taking the case where the matching result is a plaintext serial number and the purpose of identity verification is only to confirm whether the target user identifier is correct but the target user biometric information is incorrect, if the matching result of the target user identifier obtained by the first service device contains the serial number of the user identifier that matches it in the database, and the matching result of the target user biometric information does not contain any serial number, then it can be determined that the target user meets the verification target, that is, it is determined that the target user identifier provided by the target user is correct but the target user biometric information is incorrect, and further, it can be determined that the target user may be using the fingerprint of other users, or using a virtual fingerprint, or the fingerprint has changed, so that corresponding measures are executed, etc. This specification does not make specific limitations on this.
[0137] Exemplarily, taking the case where the matching result is a plaintext serial number and the purpose of identity verification is only to confirm whether the target user's biometric information is correct but the target user's identifier is incorrect, if the matching result of the target user's identifier obtained by the first service device does not contain any serial number, and the matching result of the target user's biometric information contains the serial number of the user's biometric information that matches it in the database, then it can be determined that the target user meets the verification target, that is, it is determined that the target user's biometric information provided by the target user is correct but the target user identifier is incorrect, and further, it can be determined that the target user may be using the mobile phone number of another user, or a virtual mobile phone number, or the mobile phone number has changed, and corresponding measures can be executed, etc. This specification does not make specific limitations on this.
[0138] Corresponding to the implementation of the above method flow, the embodiment of this specification also provides an identity verification device, which is applied to a first service device corresponding to the identity verification party, and the database of the second service device corresponding to the identity information storage party can maintain multiple users' identity information, and the identity information can include user identification and user biometric information. Figure 4 , Figure 4 FIG. 1 is a schematic diagram of a structure of an identity verification device provided by an exemplary embodiment. Figure 4 As shown, the device 40 includes:
[0139] An acquisition unit 401 is used to acquire a target user identifier and target user biometric information corresponding to a target user to be verified;
[0140] A user identification matching unit 402 is configured to perform multi-party secure computation on the target user identification and multiple user identifications in the database to determine whether the target user identification matches the multiple user identifications; and
[0141] A user biometric information matching unit 403, configured to perform multi-party secure computing on the target user biometric information and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information;
[0142] The identity verification unit 404 is used to verify the identity of the target user according to the matching result of the target user identification and the matching result of the target user biometric information.
[0143] In an illustrated implementation manner, the user identification matching unit 402 is specifically configured to:
[0144] Running a secure equality determination algorithm to perform multi-party secure computation on the target user identifier and multiple user identifiers in the database to determine whether the target user identifier is equal to each user identifier in the multiple user identifiers;
[0145] If the target user identifier is equal to any user identifier among the multiple user identifiers, it is determined that the target user identifier is matched successfully, otherwise, the match fails.
[0146] In an illustrated embodiment, the secure equality determination algorithm includes a secure equality determination algorithm based on secret sharing, or a secure equality determination algorithm based on a confusion circuit.
[0147] In an illustrated implementation manner, the user identification matching unit 402 is specifically configured to:
[0148] Running a privacy intersection algorithm to perform multi-party secure computation on the target user identifier and multiple user identifiers in the database to obtain an intersection between the target user identifier and the multiple user identifiers;
[0149] If the calculated intersection is the target user identifier, it is determined that the target user identifier is matched successfully; otherwise, the match fails.
[0150] In an illustrated embodiment, the user biometric information includes a vector representing a biometric feature of the user; the user biometric information matching unit 403 is specifically configured to:
[0151] Running a vector similarity algorithm based on secret sharing, performing multi-party secure computation on the target user biometric information and multiple user biometric information in the database, so as to obtain a vector similarity between the target user biometric information and each user biometric information in the multiple user biometric information;
[0152] If the vector similarity between the target user biometric information and any user biometric information among the multiple user biometric information is greater than a preset threshold, it is determined that the target user biometric information is matched successfully, otherwise, the match fails.
[0153] In an illustrated embodiment, the vector similarity algorithm includes a cosine similarity algorithm or a Hamming similarity algorithm.
[0154] In an illustrated embodiment, the database further maintains a plurality of serial numbers corresponding to the plurality of user identifiers and the plurality of user biometric information, wherein the serial numbers corresponding to the user identifier and the user biometric information of the same user are the same;
[0155] If the target user identifier is matched successfully, the matching result of the target user identifier includes the sequence number of the user identifier that matches the target user identifier among the multiple user identifiers;
[0156] If the target user biometric information is matched successfully, the matching result of the target user biometric information includes the sequence number of the user biometric information that matches the target user biometric information among the multiple user biometric information.
[0157] In an illustrated embodiment, the identity verification unit 404 is specifically configured to:
[0158] If at least one of the target user identification and the target user biometric information fails to match, determining that the identity verification of the target user fails;
[0159] If the target user identifier and the target user biometric information are both matched successfully, further comparing whether the serial number included in the matching result of the target user identifier is the same as the serial number included in the matching result of the user biometric information;
[0160] If they are the same, it is determined that the identity verification of the target user has passed; otherwise, it is determined that the identity verification of the target user has failed.
[0161] In an illustrated embodiment, the matching result of the target user identifier includes a first secret state vector, and the first secret state vector includes multiple elements corresponding to the matching results between the target user identifier and the multiple user identifiers; wherein the value of an element is 0, indicating that the user identifier corresponding to the element does not match the target user identifier, and the value of an element is 1, indicating that the user identifier corresponding to the element matches the target user identifier;
[0162] The matching result of the target user's biometric information includes a second secret state vector, which includes multiple elements corresponding to the matching results between the target user's biometric information and the multiple user biometric information; wherein, the value of an element is 0, indicating that the user biometric information corresponding to the element does not match the target user's biometric information, and the value of an element is 1, indicating that the user biometric information corresponding to the element matches the target user's biometric information.
[0163] In an illustrated embodiment, the identity verification unit 404 is specifically configured to:
[0164] Performing secure multiplication calculation on each element in the first dense state vector and the element at the corresponding position in the second dense state vector to obtain a multiplication result vector;
[0165] The number of elements with a value of 1 in the multiplication result vector is counted, and the identity of the target user is verified according to the statistical result.
[0166] In an illustrated embodiment, the identity verification unit 404 is specifically configured to:
[0167] If the value of one of the multiple elements included in the multiplication result vector is 1, it is determined that the identity verification of the target user has passed;
[0168] If the values of the multiple elements included in the multiplication result vector are all 0, it is determined that the identity verification of the target user has failed.
[0169] In an illustrated embodiment, the identity verification unit 404 is specifically configured to:
[0170] Perform a secure XOR calculation on each element in the first secret state vector and the element at the corresponding position in the second secret state vector to obtain an XOR result vector;
[0171] The number of elements with a value of 1 in the XOR result vector is counted, and the identity of the target user is verified according to the statistical result.
[0172] In an illustrated embodiment, the identity verification unit 404 is specifically configured to:
[0173] If at least one of the multiple elements included in the XOR result vector has a value of 1, it is determined that the identity verification of the target user fails;
[0174] If the multiple elements included in the XOR result vector are all 0, it is determined that the identity verification of the target user has failed or passed.
[0175] The implementation process of the functions and effects of each unit in the above-mentioned device 40 is specifically described in the above-mentioned embodiment, and will not be repeated here. It should be understood that the above-mentioned device 40 can be implemented by software, or by hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by the processor (Central Process Unit, CPU) of the device where it is located reading the corresponding computer program instructions into the memory and running them. From the hardware level, in addition to the CPU and memory, the device where the above-mentioned device is located usually also includes other hardware such as chips for wireless signal transmission and reception, and / or other hardware such as boards and cards for realizing network communication functions.
[0176] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the units or modules may be selected according to actual needs to achieve the purpose of the scheme of this specification. Those of ordinary skill in the art may understand and implement it without creative work.
[0177] The devices, units, and modules described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0178] Corresponding to the above method embodiment, the embodiment of this specification also provides a computing device. Figure 5 , Figure 5 It is a structural diagram of a computing device provided by an exemplary embodiment. Figure 5 The computing device shown may be Figure 1 In the system architecture shown, the service device 100 corresponding to the identity verification party, wherein the second service device (eg, Figure 1 The database of the service device 200 shown in FIG. 1 maintains identity information of multiple users, which may include user identification and user biometric information. Figure 5 As shown, the computing device includes a processor 1001 and a memory 1002, and may further include an input device 1004 (such as a keyboard, etc.) and an output device 1005 (such as a display, etc.). The processor 1001, the memory 1002, the input device 1004, and the output device 1005 may be connected via a bus or other means. Figure 5 As shown, the memory 1002 includes a computer-readable storage medium 1003, which stores a computer program that can be run by the processor 1001. The processor 1001 can be a CPU, a microprocessor, or an integrated circuit for controlling the execution of the above method embodiment. When the processor 1001 runs the stored computer program, it can execute the various steps of the identity verification method in the embodiment of this specification, including: obtaining a target user identifier and target user biometric information corresponding to the target user to be verified; performing multi-party secure calculations on the target user identifier and multiple user identifiers in the database to determine whether the target user identifier matches the multiple user identifiers; and performing multi-party secure calculations on the target user biometric information and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information; according to the matching result of the target user identifier and the matching result of the target user biometric information, verify the identity of the target user, and so on.
[0179] For a detailed description of each step of the above identity verification method, please refer to the previous content and will not be repeated here.
[0180] Corresponding to the above method embodiment, the embodiment of this specification also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by the processor, it executes each step of the identity verification method in the embodiment of this specification. Please refer to the description of the above embodiment for details, which will not be repeated here.
[0181] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.
[0182] In a typical configuration, a terminal device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0183] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0184] Computer readable media include permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer readable instructions, data structures, program modules or other data.
[0185] Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.
[0186] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0187] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, the embodiments of this specification may take the form of complete hardware embodiments, complete software embodiments or embodiments combining software and hardware. Moreover, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
Claims
1. An identity verification method, characterized in that: The method is applied to a first service device corresponding to an identity verification party, and a second service device corresponding to an identity information storage party maintains identity information of multiple users in a database, wherein the identity information includes user identification and user biometric information; the method includes: Obtaining a target user identifier and target user biometric information corresponding to the target user to be verified; performing multi-party secure computation on the target user identifier and multiple user identifiers in the database to determine whether the target user identifier matches the multiple user identifiers; and, Performing multi-party secure computing on the target user biometric information and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information; The identity of the target user is verified according to the matching result of the target user identification and the matching result of the target user biometric information.
2. The method according to claim 1, characterized in that: The performing multi-party secure computation on the target user identifier and the multiple user identifiers in the database to determine whether the target user identifier matches the multiple user identifiers includes: Running a secure equality determination algorithm to perform multi-party secure computation on the target user identifier and multiple user identifiers in the database to determine whether the target user identifier is equal to each user identifier in the multiple user identifiers; If the target user identifier is equal to any user identifier among the multiple user identifiers, it is determined that the target user identifier is matched successfully, otherwise, the match fails.
3. The method according to claim 2, characterized in that The secure equality determination algorithm includes a secure equality determination algorithm based on secret sharing, or a secure equality determination algorithm based on a confusion circuit.
4. The method according to claim 1, characterized in that: The performing multi-party secure computation on the target user identifier and the multiple user identifiers in the database to determine whether the target user identifier matches the multiple user identifiers includes: Running a privacy intersection algorithm to perform multi-party secure computation on the target user identifier and multiple user identifiers in the database to obtain an intersection between the target user identifier and the multiple user identifiers; If the calculated intersection is the target user identifier, it is determined that the target user identifier is matched successfully; otherwise, the match fails.
5. The method according to claim 2 or 4, characterized in that: The user biometric information includes a vector representing a biometric feature of the user; the multi-party secure computation is performed on the target user biometric information and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information, including: Running a vector similarity algorithm based on secret sharing, performing multi-party secure computation on the target user biometric information and multiple user biometric information in the database, so as to obtain a vector similarity between the target user biometric information and each user biometric information in the multiple user biometric information; If the vector similarity between the target user biometric information and any user biometric information among the multiple user biometric information is greater than a preset threshold, it is determined that the target user biometric information is matched successfully, otherwise, the match fails.
6. The method according to claim 5, characterized in that The vector similarity algorithm includes a cosine similarity algorithm or a Hamming similarity algorithm.
7. The method according to claim 5, characterized in that The database further maintains a plurality of serial numbers corresponding to the plurality of user identifiers and the plurality of user biometric information, wherein the serial numbers corresponding to the user identifier and the user biometric information of the same user are the same; If the target user identifier is matched successfully, the matching result of the target user identifier includes the sequence number of the user identifier that matches the target user identifier among the multiple user identifiers; If the target user biometric information is matched successfully, the matching result of the target user biometric information includes the sequence number of the user biometric information that matches the target user biometric information among the multiple user biometric information.
8. The method according to claim 7, characterized in that The performing identity verification on the target user according to the matching result of the target user identifier and the matching result of the target user biometric information includes: If at least one of the target user identification and the target user biometric information fails to match, determining that the identity verification of the target user fails; If the target user identifier and the target user biometric information are both matched successfully, further comparing whether the serial number included in the matching result of the target user identifier is the same as the serial number included in the matching result of the user biometric information; If they are the same, it is determined that the identity verification of the target user has passed; otherwise, it is determined that the identity verification of the target user has failed.
9. The method according to claim 5, characterized in that The matching result of the target user identifier includes a first encrypted state vector, wherein the first encrypted state vector includes multiple elements corresponding to the matching results between the target user identifier and the multiple user identifiers; wherein a value of an element is 0, indicating that the user identifier corresponding to the element does not match the target user identifier, and a value of an element is 1, indicating that the user identifier corresponding to the element matches the target user identifier; The matching result of the target user's biometric information includes a second secret state vector, which includes multiple elements corresponding to the matching results between the target user's biometric information and the multiple user biometric information; wherein, the value of an element is 0, indicating that the user biometric information corresponding to the element does not match the target user's biometric information, and the value of an element is 1, indicating that the user biometric information corresponding to the element matches the target user's biometric information.
10. The method according to claim 9, characterized in that The performing identity verification on the target user according to the matching result of the target user identifier and the matching result of the target user biometric information includes: Performing secure multiplication calculation on each element in the first dense state vector and the element at the corresponding position in the second dense state vector to obtain a multiplication result vector; The number of elements with a value of 1 in the multiplication result vector is counted, and the identity of the target user is verified according to the statistical result.
11. The method according to claim 10, characterized in that The verifying the identity of the target user according to the statistical results includes: If the value of one of the multiple elements included in the multiplication result vector is 1, it is determined that the identity verification of the target user has passed; If the values of the multiple elements included in the multiplication result vector are all 0, it is determined that the identity verification of the target user has failed.
12. The method according to claim 9, characterized in that The performing identity verification on the target user according to the matching result of the target user identifier and the matching result of the target user biometric information includes: Performing a secure XOR calculation on each element in the first secret state vector and the element at the corresponding position in the second secret state vector to obtain an XOR result vector; The number of elements with a value of 1 in the XOR result vector is counted, and the identity of the target user is verified according to the statistical result.
13. The method according to claim 12, characterized in that The verifying the identity of the target user according to the statistical results includes: If at least one of the multiple elements included in the XOR result vector has a value of 1, it is determined that the identity verification of the target user fails; If the multiple elements included in the XOR result vector are all 0, it is determined that the identity verification of the target user has failed or passed.
14. An identity verification device, characterized in that: The device is applied to a first service device corresponding to an identity verification party, and a second service device corresponding to an identity information storage party maintains identity information of multiple users in a database, wherein the identity information includes user identification and user biometric information; the device includes: An acquisition unit, used to acquire a target user identification and target user biometric information corresponding to the target user to be verified; A user identification matching unit is used to perform multi-party security calculation on the target user identification and multiple user identifications in the database to determine whether the target user identification matches the multiple user identifications; and A user biometric information matching unit, configured to perform multi-party secure computing on the target user biometric information and multiple user biometric information in the database to determine whether the target user biometric information matches the multiple user biometric information; The identity verification unit is used to verify the identity of the target user according to the matching result of the target user identification and the matching result of the target user biometric information.
15. A computing device, characterized in that: include: Memory and processor; The memory has stored thereon computer programs / instructions executable by the processor; When the processor runs the computer program / instructions, it performs the method according to any one of claims 1 to 13.
16. A computer-readable storage medium, characterized in that: A computer program / instruction is stored thereon, and when the computer program / instruction is executed by a processor, the method according to any one of claims 1 to 13 is implemented.
17. A computer program product, characterized in that The computer program product comprises a computer program / instruction, and when the computer program / instruction is executed by a processor, the method according to any one of claims 1 to 13 is implemented.
