Login authentication system, method, computer device, computer readable storage medium, and computer program product

By introducing homomorphic encryption technology and distributed key management into the user login authentication system, the problem of low privacy and security caused by the existence of user data plain text is solved, data encryption and behavior detection during the authentication process is realized, and users are significantly improved Data security.

CN118890167APending Publication Date: 2024-11-01SHENZHEN COMTOP INFORMATION TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410835393.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-26
Publication Date
2024-11-01

AI Technical Summary

Technical Problem

In the existing user login authentication system, the data exists in plain text, resulting in low user privacy and security and difficulty in effectively protecting.

Method used

A login authentication system has been designed, including a login authentication module, a key management module, a data encryption module and a behavior detection module. Through homomorphic encryption technology and distributed key storage, data security during the authentication process is ensured and the user is in the process of After logging in, encrypt and behavioral detection of uploaded data.

Benefits of technology

Improves the security of user data, prevents data breaches and unauthorized access, and ensures the protection of user privacy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118890167A_ABST
    Figure CN118890167A_ABST
Patent Text Reader

Abstract

The invention relates to a login authentication system and method, computer equipment, a computer readable storage medium and a computer program product, and relates to the technical field of user login authentication. The system comprises a login authentication module used for acquiring a homomorphic encryption private key corresponding to a distributed storage user through a secret key management module, and based on the homomorphic encryption private key corresponding to the user, a pre-stored first encryption login password of the user and a pre-stored first encryption biological characteristic of the user, performing login authentication on the user according to the homomorphic encryption private key corresponding to the user; verifying a second encrypted login password and a second encrypted biological feature carried by the login request; the data encryption module is used for encrypting data uploaded to the login authentication system by the user through the terminal; and the behavior detection module is used for carrying out abnormal information detection on the behavior information of the user in the login authentication system, and sending an abnormal prompt for the user under the condition that abnormal information exists in the behavior information. By adopting the system, the data security of the user can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of user login authentication, and in particular to a login authentication method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] User login authentication is the process of confirming the identity of the operator by the computer and network system. In the related art, the data used in the authentication process exists in plain text. Therefore, once the data is exposed, the user's privacy will lose protection, making the user's data security low. Summary of the invention

[0003] Based on this, it is necessary to provide a login authentication system, method, computer device, computer-readable storage medium and computer program product that can improve user data security in response to the above technical problems.

[0004] In a first aspect, the present application provides a login authentication system, including a login authentication module, a key management module, a data encryption module and a behavior detection module;

[0005] The login authentication module is used to, upon receiving a login request sent by a user through a terminal, obtain the distributedly stored homomorphic encryption private key corresponding to the user through the key management module, and verify the second encrypted login password and the second encrypted biometric feature carried by the login request based on the homomorphic encryption private key corresponding to the user, the pre-stored first encrypted login password of the user, and the pre-stored first encrypted biometric feature of the user, and allow the user to log in to the login authentication system after the verification is passed;

[0006] The key management module is used for distributed storage of homomorphic encryption private keys corresponding to the users;

[0007] The data encryption module is used to encrypt the data uploaded by the user to the login authentication system through the terminal after the user logs in to the login authentication system;

[0008] The behavior detection module is used to detect abnormal information on the behavior information of the user in the login authentication system after the user logs in to the login authentication system, and issue an abnormal prompt to the user if there is abnormal information in the behavior information;

[0009] Among them, the terminal stores the homomorphic encryption public key corresponding to the user; the second encrypted login password is obtained by the terminal encrypting the login password input by the user based on the homomorphic encryption public key corresponding to the user; the second encrypted biometric feature is obtained by the terminal encrypting the collected biometric feature of the user based on the homomorphic encryption public key corresponding to the user.

[0010] In one of the embodiments, the login authentication module is further configured to send a key generation request corresponding to the user to the key management module when receiving a registration request sent by the user;

[0011] The key management module is further used to generate a homomorphic encryption private key corresponding to the user and a homomorphic encryption public key corresponding to the user in response to a key generation request corresponding to the user, and to perform distributed storage on the homomorphic encryption private key corresponding to the user and the homomorphic encryption public key corresponding to the user;

[0012] The login authentication module is further configured to obtain the homomorphic encryption public key corresponding to the user through the key management module; encrypt the login password carried in the registration request based on the homomorphic encryption public key corresponding to the user to obtain the first encrypted login password, and encrypt the biometric feature carried in the registration request to obtain the first encrypted biometric feature; and store the first encrypted login password and the first encrypted biometric feature;

[0013] The key management module is also used to send the homomorphic encryption public key corresponding to the user to the terminal after the login authentication module stores the first encrypted login password and the first encrypted biometric feature.

[0014] In one of the embodiments, the login authentication module is further used to send a private key acquisition request corresponding to the user to the key management module when it is necessary to obtain the homomorphic encryption private key corresponding to the user through the key management module;

[0015] The key management module is also used to respond to the key acquisition request, determine the target distributed storage nodes for storing the key fragments of the homomorphically encrypted private key corresponding to the user from the distributed storage nodes corresponding to the login authentication system; forward the key acquisition request to each target distributed storage node to obtain the private key fragments stored on each target distributed storage node; combine the private key fragments stored on the target distributed storage nodes to obtain the homomorphically encrypted private key corresponding to the user; and feed back the homomorphically encrypted private key corresponding to the user to the login authentication module.

[0016] In one of the embodiments, the key management module is also used to forward the key acquisition request to the distributed backup node corresponding to the failed target distributed storage node when any one of the target distributed storage nodes fails, so as to obtain the private key fragment backed up on the distributed backup node.

[0017] In one of the embodiments, the login authentication module is also used to encrypt the verification result of the second encrypted login password and the second encrypted biometric feature based on the homomorphic encryption private key corresponding to the user, obtain the encrypted verification result, and send the encrypted verification result to the terminal; the terminal is used to decrypt the encrypted verification result based on the homomorphic encryption public key corresponding to the user, and log in to the login authentication system when the verification result obtained by decryption is verification passed.

[0018] In one of the embodiments, the data encryption module is also used to add Laplace noise to the data uploaded by the user to the login authentication system through the terminal after the user logs in to the login authentication system, so as to obtain the data after the noise is added; and perform differential privacy encryption processing on the data after the noise is added.

[0019] In a second aspect, the present application also provides a login authentication method, which is applied to a login authentication system, comprising:

[0020] Upon receiving a login request sent by a user through a terminal, obtaining a homomorphic encryption private key corresponding to the user in distributed storage, and verifying the second encrypted login password and the second encrypted biometric feature carried by the login request based on the homomorphic encryption private key corresponding to the user, the pre-stored first encrypted login password of the user, and the pre-stored first encrypted biometric feature of the user, and allowing the user to log in to the login authentication system after the verification is passed;

[0021] After the user logs in to the login authentication system, encrypt the data uploaded by the user to the login authentication system through the terminal, and perform behavior detection on the user's behavior under the login authentication system, and issue an abnormal prompt to the user if there is abnormal behavior in the behavior;

[0022] Among them, the terminal stores the homomorphic encryption public key corresponding to the user; the second encrypted login password is obtained by the terminal encrypting the login password input by the user based on the homomorphic encryption public key corresponding to the user; the second encrypted biometric feature is obtained by the terminal encrypting the collected biometric feature of the user based on the homomorphic encryption public key corresponding to the user.

[0023] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0024] Upon receiving a login request sent by a user through a terminal, obtaining a homomorphic encryption private key corresponding to the user in distributed storage, and verifying the second encrypted login password and the second encrypted biometric feature carried by the login request based on the homomorphic encryption private key corresponding to the user, the pre-stored first encrypted login password of the user, and the pre-stored first encrypted biometric feature of the user, and allowing the user to log in to the login authentication system after the verification is passed;

[0025] After the user logs in to the login authentication system, encrypt the data uploaded by the user to the login authentication system through the terminal, and perform behavior detection on the user's behavior under the login authentication system, and issue an abnormal prompt to the user if there is abnormal behavior in the behavior;

[0026] Among them, the terminal stores the homomorphic encryption public key corresponding to the user; the second encrypted login password is obtained by the terminal encrypting the login password input by the user based on the homomorphic encryption public key corresponding to the user; the second encrypted biometric feature is obtained by the terminal encrypting the collected biometric feature of the user based on the homomorphic encryption public key corresponding to the user.

[0027] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0028] Upon receiving a login request sent by a user through a terminal, obtaining a homomorphic encryption private key corresponding to the user in distributed storage, and verifying the second encrypted login password and the second encrypted biometric feature carried by the login request based on the homomorphic encryption private key corresponding to the user, the pre-stored first encrypted login password of the user, and the pre-stored first encrypted biometric feature of the user, and allowing the user to log in to the login authentication system after the verification is passed;

[0029] After the user logs in to the login authentication system, encrypt the data uploaded by the user to the login authentication system through the terminal, and perform behavior detection on the user's behavior under the login authentication system, and issue an abnormal prompt to the user if there is abnormal behavior in the behavior;

[0030] Among them, the terminal stores the homomorphic encryption public key corresponding to the user; the second encrypted login password is obtained by the terminal encrypting the login password input by the user based on the homomorphic encryption public key corresponding to the user; the second encrypted biometric feature is obtained by the terminal encrypting the collected biometric feature of the user based on the homomorphic encryption public key corresponding to the user.

[0031] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0032] Upon receiving a login request sent by a user through a terminal, obtaining a homomorphic encryption private key corresponding to the user in distributed storage, and verifying the second encrypted login password and the second encrypted biometric feature carried by the login request based on the homomorphic encryption private key corresponding to the user, the pre-stored first encrypted login password of the user, and the pre-stored first encrypted biometric feature of the user, and allowing the user to log in to the login authentication system after the verification is passed;

[0033] After the user logs in to the login authentication system, encrypt the data uploaded by the user to the login authentication system through the terminal, and perform behavior detection on the user's behavior under the login authentication system, and issue an abnormal prompt to the user if there is abnormal behavior in the behavior;

[0034] Among them, the terminal stores the homomorphic encryption public key corresponding to the user; the second encrypted login password is obtained by the terminal encrypting the login password input by the user based on the homomorphic encryption public key corresponding to the user; the second encrypted biometric feature is obtained by the terminal encrypting the collected biometric feature of the user based on the homomorphic encryption public key corresponding to the user.

[0035] The above-mentioned login authentication system, method, computer device, computer-readable storage medium and computer program product, first, when the login authentication module receives a login request sent by the user through the terminal, it obtains the distributedly stored homomorphic encryption private key corresponding to the user through the key management module, and verifies the second encrypted login password and the second encrypted biometric carried in the login request based on the homomorphic encryption private key corresponding to the user, the pre-stored first encrypted login password of the user and the pre-stored first encrypted biometric of the user, and allows the user to log in to the login authentication system after the verification is passed; then, after the user logs in to the login authentication system, the data encryption module encrypts the data uploaded by the user to the login authentication system through the terminal, and the behavior detection module detects abnormal information on the user's behavior information under the login authentication system, and issues an abnormal prompt to the user when there is abnormal information in the behavior information; wherein the terminal stores the homomorphic encryption public key corresponding to the user; the second encrypted login password is obtained by the terminal encrypting the login password input by the user based on the homomorphic encryption public key corresponding to the user; the second encrypted biometric is obtained by the terminal encrypting the collected biometric of the user based on the homomorphic encryption public key corresponding to the user. In this way, by using the first encrypted login password, the first encrypted biometric, the second encrypted login password and the second encrypted biometric in an encrypted state during the authentication process, the security of the data used in the authentication process can be guaranteed, thereby ensuring the user's data security, and by encrypting the uploaded data after the user logs into the authentication system and detecting the user's behavior, the user's privacy can be further protected and the user's data security can be guaranteed; therefore, based on the above-mentioned login authentication system, the user's data security can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] FIG1 is a structural block diagram of a login authentication system in one embodiment;

[0038] FIG2 is a schematic diagram of a flow chart of a login authentication method in one embodiment;

[0039] FIG3 is a flow chart of steps for implementing user registration in one embodiment;

[0040] FIG4 is a flowchart of steps for allowing a user to log into a login authentication system after passing verification in one embodiment;

[0041] FIG5 is a schematic flow diagram of steps for obtaining a homomorphic encryption public key corresponding to a user in distributed storage in one embodiment;

[0042] FIG. 6 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] It should be noted that 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 relevant regulations.

[0045] In an exemplary embodiment, as shown in FIG. 1 , a login authentication system is provided, which can be mounted on a server or a terminal, or in a system including a server and a terminal, and implemented through the interaction between the server and the terminal; wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services; the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc.

[0046] Referring to FIG. 1 , the login authentication system includes a login authentication module, a key management module, a data encryption module and a behavior detection module.

[0047] The login authentication module is used to obtain the homomorphic encryption private key corresponding to the user in distributed storage through the key management module when receiving a login request sent by the user through the terminal, and verify the second encrypted login password and the second encrypted biometric carried by the login request based on the homomorphic encryption private key corresponding to the user, the pre-stored first encrypted login password of the user and the pre-stored first encrypted biometric of the user, and allow the user to log in to the login authentication system after the verification is passed.

[0048] The terminal is a terminal used by a user to log into the login authentication system, and may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and the like.

[0049] Among them, an application program for logging into the authentication system is installed on the terminal, and the user logs into the authentication system through the installed application program.

[0050] Among them, the terminal stores the homomorphic encryption public key corresponding to the user; the homomorphic encryption private key and homomorphic encryption public key corresponding to the user are generated and distributedly stored by the key management module when the user registers and logs in to the authentication system.

[0051] Among them, the first encrypted login password and the first encrypted biometric feature are obtained by encrypting the login password and biometric feature uploaded by the user based on the homomorphic encryption public key corresponding to the user when the user registers for the login authentication system.

[0052] Among them, the second encrypted login password is obtained by the terminal encrypting the login password input by the user based on the homomorphic encryption public key corresponding to the user; the second encrypted biometric feature is obtained by the terminal encrypting the collected biometric feature of the user based on the homomorphic encryption public key corresponding to the user.

[0053] Among them, biometric features include but are not limited to facial features, fingerprint features, pupil features, and other biometric features that can uniquely identify a user.

[0054] Specifically, when the user needs to log in to the login authentication system, he enters the user name and login password on the application and allows the application to collect his own biometrics; then, the terminal homomorphically encrypts the login password and biometrics based on the stored homomorphic encryption public key corresponding to the user, obtains a second encrypted login password and a second encrypted biometric, and generates a login request based on the user name, the second encrypted login password and the second encrypted biometric, and then sends the login request to the login authentication system.

[0055] After receiving the user's login request, the login authentication module obtains the homomorphic encryption private key corresponding to the user from the key management module through the user name, and obtains the pre-stored first encrypted login password of the user and the pre-stored first encrypted biometric feature of the user through the user name.

[0056] Next, the login authentication module decrypts the first encrypted login password based on the homomorphic encryption private key to obtain the first decrypted login password, decrypts the first encrypted biometric feature to obtain the first decrypted biometric feature, decrypts the second encrypted login password to obtain the second decrypted login password, and decrypts the second encrypted biometric feature to obtain the second decrypted biometric feature.

[0057] Finally, the login authentication module verifies the second decrypted login password based on the first decrypted login password, and verifies the second decrypted biometric feature based on the first decrypted biometric feature, and allows the user to log in to the login authentication system if both the second decrypted login password and the second decrypted biometric feature are verified.

[0058] In actual application, referring to FIG. 1 , the login authentication module implements verification by determining through a verification unit whether the first decrypted login password and the second decrypted login password are consistent, and whether the first decrypted biometric feature and the second decrypted biometric feature are consistent.

[0059] In actual applications, the login authentication module can also utilize the characteristics of homomorphic encryption to verify the second encrypted login password and the second encrypted biometric feature, that is, the second encrypted login password and the second encrypted biometric feature are decrypted by the homomorphic encryption private key to obtain the second decrypted login password and the second decrypted biometric feature, and then the same operation is performed on the first encrypted login password and the second decrypted login password to determine whether the operation results of the two are the same, and the same operation is performed on the first encrypted biometric feature and the second decrypted biometric feature to determine whether the operation results of the two are the same.

[0060] The data encryption module is used to encrypt the data uploaded by the user to the login authentication system through the terminal after the user logs in to the login authentication system.

[0061] Specifically, after the user successfully logs into the login authentication system, the data encryption module will encrypt and store the data uploaded by the user to the login authentication system, especially sensitive data involving privacy.

[0062] Among them, the encryption of data specifically adopts differential privacy encryption processing that introduces Laplace noise.

[0063] The behavior detection module is used to detect abnormal information of the user's behavior information under the login authentication system after the user logs in to the login authentication system, and issue an abnormal prompt to the user when there is abnormal information in the behavior information.

[0064] Specifically, after the user successfully logs into the login authentication system, the behavior detection module will monitor the user's use of the login authentication system in real time, and then obtain the user's behavior information under the login authentication system, and perform abnormal information detection on the behavior information. When abnormal information is detected in the behavior information, an abnormal prompt is issued to the user, so that the login authentication system can take corresponding measures against the user to protect the user's data security.

[0065] In actual applications, after detecting abnormal information, the behavior detection module will also conduct a risk assessment on the abnormal information and issue corresponding abnormal prompts based on the assessment results, so that the login authentication system can take corresponding measures against the user.

[0066] In actual applications, the user's behavior information under the login authentication system includes login time, login location, login device type, operation behavior frequency, and statistical characteristics based on historical data, including the number of user logins, the frequency of changes in login locations, etc.

[0067] In actual applications, the login authentication system takes corresponding measures for users, including strengthening identity authentication, temporarily blocking accounts, and notifying administrators.

[0068] In practical applications, the behavior detection module selects at least one of logistic regression, decision tree, random forest, and support vector machine as the abnormal information detection model to be trained, uses the historical behavior information of each user under the login authentication system for training, and uses the trained model to perform real-time detection of the user's behavior information to detect abnormal behavior information that may pose a security threat, and evaluates the detected abnormal behavior information to determine the degree of threat and the possible damage, and formulates corresponding measures.

[0069] In the above-mentioned login authentication system, first, when the login authentication module receives a login request sent by the user through the terminal, it obtains the homomorphic encryption private key corresponding to the user in distributed storage through the key management module, and verifies the second encrypted login password and the second encrypted biometric carried in the login request based on the homomorphic encryption private key corresponding to the user, the pre-stored first encrypted login password of the user and the pre-stored first encrypted biometric of the user, and allows the user to log in to the login authentication system after the verification is passed; then, after the user logs in to the login authentication system, the data encryption module encrypts the data uploaded to the login authentication system by the user through the terminal, and the behavior detection module detects abnormal information on the user's behavior information in the login authentication system, and issues an abnormal prompt to the user when there is abnormal information in the behavior information; wherein the terminal stores the homomorphic encryption public key corresponding to the user; the second encrypted login password is obtained by the terminal encrypting the login password input by the user based on the homomorphic encryption public key corresponding to the user; the second encrypted biometric is obtained by the terminal encrypting the collected biometric of the user based on the homomorphic encryption public key corresponding to the user. In this way, by using the first encrypted login password, the first encrypted biometric, the second encrypted login password and the second encrypted biometric in an encrypted state during the authentication process, the security of the data used in the authentication process can be guaranteed, thereby ensuring the user's data security, and by encrypting the uploaded data after the user logs into the authentication system and detecting the user's behavior, the user's privacy can be further protected and the user's data security can be guaranteed; therefore, based on the above-mentioned login authentication system, the user's data security can be improved.

[0070] In an exemplary embodiment, the login authentication module is further configured to send a key generation request corresponding to the user to the key management module upon receiving a registration request sent by the user.

[0071] Specifically, when a user needs to register and log in to the authentication system, he enters the username and login password for registration on the application and allows the application to collect his own biometrics; then, the terminal generates a registration request based on the username, login password and biometrics, and then sends the registration request to the login authentication system.

[0072] When receiving a registration request sent by a user, the login authentication module generates a key generation request for the user, and sends the key generation request corresponding to the user to the key management module to request the key management module to generate a key corresponding to the user.

[0073] In actual applications, the process of an application collecting its own biometric features is as follows: Referring to FIG. 1 , the application collects a user's biometric image and identifies the biometric image through a biometric feature identification unit to extract the biometric features.

[0074] Furthermore, the biometric recognition unit recognizes biological images and extracts biological features using a convolutional neural network: convolution kernels of different sizes are used in the convolution layer to extract features of different scales, and the feature maps generated by convolution kernels of different scales are fused; a self-attention module is added after the convolution layer to improve the effectiveness of feature representation by calculating the correlation within the feature map, and a channel attention mechanism is introduced to weight the feature maps of different channels and suppress redundant features.

[0075] In practical applications, convolutional neural networks include multiple convolutional layers, pooling layers, and fully connected layers.

[0076] In the convolution layer, multiple convolution kernels are used to extract features from the input image. As shown in Formula 1, each convolution kernel generates a feature map:

[0077] (Formula 1)

[0078] in, Indicates Layer location The pixel value of the feature map, It is The convolution kernel parameters of the layer, It is Layer location The pixel value of the feature map, It is The bias term of the layer, is the activation function, and Indicates the convolution kernel in the input image The position on the layer, and It is The size of the layer input image, which represents the number of rows and columns of the input image, and Indicates the position of the convolution kernel on the feature map of the current layer.

[0079] As shown in Formula 2, each feature map is downsampled using average pooling:

[0080] (Formula 2)

[0081] in, It is The pixel value of the feature map after pooling of the layer, is the pooling function.

[0082] Next, the output of the pooling layer is flattened into a one-dimensional vector, and then passed through multiple fully connected layers for feature mapping and classification as shown in Formula 3:

[0083] (Formula 3)

[0084] in, It is The output of the layer, is the weight matrix, It is The output vector of the layer, is the bias term, is the activation function.

[0085] The key management module is also used to respond to the user's corresponding key generation request, generate the user's corresponding homomorphic encryption private key and the user's corresponding homomorphic encryption public key, and distribute the user's corresponding homomorphic encryption private key and the user's corresponding homomorphic encryption public key.

[0086] Specifically, referring to Figure 1, the key management module responds to the key generation request corresponding to the user, and uses an asymmetric encryption algorithm to generate a homomorphic encryption private key and a homomorphic encryption public key corresponding to the user through a key generation unit, and divides the homomorphic encryption private key and the homomorphic encryption public key corresponding to the user into multiple key fragments, each of which is stored in a distributed storage node corresponding to the login authentication system to realize distributed storage of keys.

[0087] In practical applications, the homomorphic encryption public key and the homomorphic encryption private key can be a fully homomorphic encryption public key and a fully homomorphic encryption private key, or a partially homomorphic encryption public key and a partially homomorphic encryption private key. The specific selection is based on the sensitivity of the user's login password and biometric features. When the sensitivity is high, the fully homomorphic encryption key is used, and when the sensitivity is low, the partially homomorphic encryption key is used.

[0088] In practical applications, the key management module is implemented through a hardware security module (HSM) to ensure the secure generation and storage of keys.

[0089] The login authentication module is also used to obtain the homomorphic encryption public key corresponding to the user through the key management module; based on the homomorphic encryption public key corresponding to the user, encrypt the login password carried in the registration request to obtain a first encrypted login password, and encrypt the biometric feature carried in the registration request to obtain a first encrypted biometric feature; store the first encrypted login password and the first encrypted biometric feature.

[0090] Specifically, after the key management module generates the homomorphic encryption public key corresponding to the user, the login authentication module obtains the homomorphic encryption public key corresponding to the user, and based on the homomorphic encryption public key corresponding to the user, encrypts the login password and biometrics carried in the registration request respectively to obtain the first encrypted login password and the first encrypted biometrics, and stores the first encrypted login password and the first encrypted biometrics to realize user registration.

[0091] In practical applications, using encryption algorithms to store passwords and biometrics can significantly reduce the risk of passwords and biometrics being cracked. Even if the database is hacked, attackers cannot directly obtain the plaintext password. In addition, before encrypting the password, the login authentication module can also add a randomly generated salt value to increase the complexity of the password and effectively prevent rainbow table attacks.

[0092] The key management module is also used to send the user's corresponding homomorphic encryption public key to the terminal after the login authentication module stores the first encrypted login password and the first encrypted biometric feature.

[0093] Specifically, referring to Figure 1, the key management module stores the first encrypted login password and the first encrypted biometric feature in the login authentication module, that is, after the user's registration is completed, the user's corresponding homomorphic encryption public key is sent to the terminal through the key distribution backup unit.

[0094] In this embodiment, by encrypting the login password and biometrics used by the user for registration, it is possible to ensure that the data exists in an encrypted state, thereby improving the data security of the user. In addition, by distributing the key storage, the key security of the user can also be further increased.

[0095] In an exemplary embodiment, the login authentication module is also used to send a private key acquisition request corresponding to the user to the key management module when it is necessary to obtain the homomorphic encryption private key corresponding to the user through the key management module.

[0096] Specifically, during the process of user registration or user login, the login authentication module needs to obtain the user's corresponding homomorphic encryption private key through the key management module. Therefore, based on the user's username, a private key acquisition request corresponding to the user is generated and sent to the key management module.

[0097] The key management module is also used to respond to the key acquisition request, determine the target distributed storage nodes for storing the key fragments of the homomorphically encrypted private key corresponding to the user from the distributed storage nodes corresponding to the login authentication system; forward the key acquisition request to each target distributed storage node to obtain the private key fragments stored on each target distributed storage node; combine the private key fragments stored on each target distributed storage node to obtain the homomorphically encrypted private key corresponding to the user; and feed back the homomorphically encrypted private key corresponding to the user to the login authentication module.

[0098] Specifically, the key management module responds to the key acquisition request, and based on the user name carried in the key acquisition request, determines, from the distributed storage nodes corresponding to the login authentication system, the distributed storage nodes for storing the key fragments of the homomorphically encrypted private key corresponding to the user, as the target distributed storage nodes corresponding to the homomorphically encrypted private key corresponding to the user; then, the key management module reads the key fragments stored on each target distributed storage node, combines the key fragments to obtain the homomorphically encrypted private key corresponding to the user, and finally feeds back the homomorphically encrypted private key corresponding to the user to the login authentication module.

[0099] In this embodiment, the distributed storage of keys can further increase the security of user keys.

[0100] In an exemplary embodiment, the key management module is also used to forward the key acquisition request to the distributed backup node corresponding to the failed target distributed storage node in the event that any one of the target distributed storage nodes fails, so as to obtain the private key fragment backed up on the distributed backup node.

[0101] Specifically, in addition to the distributed storage nodes for storing key fragments, the login authentication system also includes distributed backup nodes for backing up key fragments. When any target distributed storage node among the target distributed storage nodes fails, the key management module forwards the key acquisition request that should be forwarded to the failed target distributed storage node to the distributed backup node corresponding to the failed target distributed storage node, so as to obtain the private key fragment backed up on the distributed backup node.

[0102] In actual applications, referring to Figure 1, the key management module adopts an incremental backup strategy through a key distribution backup unit to only back up changed key fragments to reduce backup time and storage overhead; among them, the changed key fragments include key fragments that are regenerated when the login authentication system is regularly rotated, security threats are discovered, or keys are leaked.

[0103] In this embodiment, when the target distributed storage node fails, the key management module can forward the key acquisition request to the corresponding backup node in time to ensure the continuity of the key service.

[0104] In an exemplary embodiment, when the key management module sends the homomorphically encrypted public key corresponding to the user to the terminal, it uses a secure authentication mechanism SSH (Secure Shell) to verify the identity of the key recipient to prevent the key from being accessed by unauthorized entities: first, the key management module establishes an SSH connection to authenticate the terminal, and after the terminal identity authentication is successful, an encrypted security channel is established to perform secure data transmission through the channel, and the key fragment of the homomorphically encrypted public key is securely transmitted to the terminal; then, after receiving the key fragment, the terminal sends a confirmation message to the login authentication system, and the login authentication system records the successful transmission.

[0105] In an exemplary embodiment, the login authentication module is also used to encrypt the verification results for the second encrypted login password and the second encrypted biometric feature based on the homomorphic encryption private key corresponding to the user, obtain the encrypted verification result, and send the encrypted verification result to the terminal.

[0106] Among them, the terminal is used to decrypt the encrypted verification result based on the homomorphic encryption public key corresponding to the user, and log in to the authentication system when the decrypted verification result is verification passed.

[0107] Specifically, after obtaining the verification results for the second encrypted login and the second encrypted biometric feature, the login authentication module will also encrypt the verification results based on the user's corresponding homomorphic encryption private key, obtain the encrypted verification result, and send the encrypted verification result to the terminal; after the terminal receives the encrypted verification result, it decrypts the encrypted verification result based on the user's corresponding homomorphic encryption public key, and if the verification result obtained by decryption is verification passed, the user is allowed to log in to the login authentication system through the terminal.

[0108] In this embodiment, by encrypting the verification result, it is possible to prevent the verification result from being tampered with, thereby ensuring the user's data security.

[0109] In an exemplary embodiment, the data encryption module is also used to add Laplace noise to the data uploaded by the user to the login authentication system through the terminal after the user logs in to the login authentication system, so as to obtain the data with added noise; and perform differential privacy encryption processing on the data with added noise.

[0110] Specifically, referring to FIG1 , the data encryption module performs differential privacy processing on the data through the differential privacy processing unit: The data is defined as , whose dimensions are ,in is the characteristic dimension of the data. , as shown in formula 4, the data encryption module gives the data Each feature of Add Laplace noise and perform differential privacy encryption on the data after adding noise:

[0111] (Formula 4)

[0112] in, is the privacy parameter for differential privacy processing, For query function The sensitivity indicates the maximum impact of user data changes on query results; the probability density function of Laplace noise is: ,in, is the central parameter of the Laplace distribution, controlling the location of the noise, is a scale parameter that controls the size of the noise. represents the value of the random variable, that is, the size of the noise, represents the exponential function, that is, the power function of the natural exponential, where express and The absolute value difference of Represents the difference divided by the scale parameter The result is used to characterize the random variable and center parameters The difference between the two, where the scale parameter of the Laplace noise By differential privacy parameters and query function sensitivity Decision, that is ; In this process and Determined based on application scenarios and privacy protection requirements.

[0113] In this embodiment, the data encryption module performs differential privacy processing on sensitive data to protect the privacy of users; and adopts the Laplace mechanism to encrypt the data to improve the level of privacy protection.

[0114] Each module in the above login authentication system can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0115] In order to more clearly illustrate the login authentication system provided by the embodiment of the present application, the login authentication system is specifically described below with a specific embodiment, but it should be understood that the embodiment of the present application is not limited thereto. In one exemplary embodiment, the present application also provides a user login security authentication system, which specifically includes the following modules:

[0116] The user authentication module is responsible for verifying the user's identity and authorizing the user to access the system. It identifies biometric features based on fully homomorphic encryption technology and deep learning technology, and performs authentication based on the identified features.

[0117] The data encryption module uses a differential privacy mechanism to add noise to the data and encrypt the user's sensitive data.

[0118] The key management module is responsible for generating, storing and managing the keys required for encryption and decryption, and uses a hardware security module HSM and a distributed key management solution for key management and storage.

[0119] The risk analysis module is used to monitor and analyze user behavior patterns, using intelligent risk analysis combined with machine learning and big data analysis to identify and prevent security threats.

[0120] The process of a user logging into the security authentication system provided by this embodiment is as follows:

[0121] 1. User registration.

[0122] The user provides a biometric image and login password when registering; the system pre-processes the biometric image provided by the user, including denoising, contrast enhancement, and scale normalization, uses a convolutional neural network to extract features from the biometric image, and generates a feature vector. The system uses an asymmetric encryption algorithm to generate a public key and private key, and uses the public key to fully homomorphically encrypt the feature vector and login password to obtain the ciphertext, and stores the encrypted biometric feature vector and password ciphertext in the database, and sends the public key to the terminal.

[0123] 2. User logs in.

[0124] When the user logs in, he / she provides the biometric image and login password again. The terminal performs the same preprocessing and feature extraction on the new biometric image to generate a new feature vector. The terminal uses the public key to perform fully homomorphic encryption on the new feature vector and the new login password to generate a login ciphertext, which is sent to the system. After receiving the ciphertext, the system uses the private key to decrypt it to obtain the user's biometric feature vector and password. The system compares the decrypted feature vector and password with the ciphertext stored during registration to verify the user's identity.

[0125] 3. Key management.

[0126] When a user registers, the system generates the keys required for encryption and decryption through the hardware security module HSM. The generated keys are directly stored by the HSM security storage module, and a distributed key management solution is adopted to divide the keys into multiple fragments and store them on different nodes for distribution and backup.

[0127] 4. Data encryption and privacy protection.

[0128] All communications between users and the system are encrypted. When processing sensitive user data, including transaction data and personal information, the system uses a differential privacy mechanism to perform noise processing, adding Laplace noise to each feature, setting the privacy parameters of differential privacy, and using the Laplace mechanism to perturb sensitive data.

[0129] In this embodiment, firstly, biometric recognition technology and homomorphic encryption technology are introduced to make the authentication method more diversified and more secure; secondly, fully homomorphic encryption technology is adopted, and the password is effectively encrypted and protected during storage and transmission, reducing the risk of password leakage; thirdly, sensitive data is noise-processed through a differential privacy mechanism, and homomorphic encryption technology is used for biometric data, effectively improving the level of user privacy protection; finally, a hardware security module HSM and a distributed key management solution are adopted to ensure the secure generation, storage and management of keys, thereby improving the security and reliability of key management.

[0130] Based on the same inventive concept, the embodiment of the present application also provides a login authentication method applied to the above login authentication system. The implementation solution provided by the method is similar to the implementation solution recorded in the above system, so the specific limitations of one or more login authentication method embodiments provided below can refer to the above limitations on the login authentication system, and will not be repeated here. As shown in Figure 2, the method includes the following steps:

[0131] Step S202, when receiving a login request sent by the user through the terminal, obtain the homomorphic encryption private key corresponding to the user in distributed storage, and based on the homomorphic encryption private key corresponding to the user, the pre-stored first encrypted login password of the user and the pre-stored first encrypted biometric feature of the user, verify the second encrypted login password and the second encrypted biometric feature carried by the login request, and allow the user to log in to the login authentication system after the verification is passed.

[0132] Step S204, after the user logs in to the login authentication system, encrypt the data uploaded by the user to the login authentication system through the terminal, and perform behavior detection on the user's behavior under the login authentication system, and issue an abnormal prompt to the user if there is abnormal behavior in the behavior.

[0133] Among them, the terminal stores the homomorphic encryption public key corresponding to the user; the second encrypted login password is obtained by the terminal encrypting the login password entered by the user based on the homomorphic encryption public key corresponding to the user; the second encrypted biometric is obtained by the terminal encrypting the collected biometric of the user based on the homomorphic encryption public key corresponding to the user.

[0134] As shown in FIG. 3 , in an exemplary embodiment, the login authentication method provided by the present application further includes the following steps before the above step S202 to implement user registration:

[0135] Step S302, upon receiving a registration request sent by a user, generates a homomorphic encryption private key corresponding to the user and a homomorphic encryption public key corresponding to the user, and performs distributed storage on the homomorphic encryption private key corresponding to the user and the homomorphic encryption public key corresponding to the user.

[0136] Step S304, obtain the homomorphic encryption public key corresponding to the user in distributed storage.

[0137] Step S306: Based on the homomorphic encryption public key corresponding to the user, the login password carried in the registration request is encrypted to obtain a first encrypted login password, and the biometric feature carried in the registration request is encrypted to obtain a first encrypted biometric feature.

[0138] Step S308, storing the first encrypted login password and the first encrypted biometric feature.

[0139] Step S310, after storing the first encrypted login password and the first encrypted biometric feature, the homomorphic encryption public key corresponding to the user is sent to the terminal.

[0140] As shown in FIG. 4 , in an exemplary embodiment, after the verification in the above step S202 is passed, the user is allowed to log in to the authentication system, which specifically includes the following steps:

[0141] Step S402: Encrypt the verification result of the second encrypted login password and the second encrypted biometric feature based on the homomorphic encryption private key corresponding to the user to obtain an encrypted verification result.

[0142] Step S404: Send the encrypted verification result to the terminal.

[0143] Among them, the terminal is used to decrypt the encrypted verification result based on the homomorphic encryption public key corresponding to the user, and log in to the authentication system when the decrypted verification result is verification passed.

[0144] As shown in FIG. 5 , in an exemplary embodiment, the above step S202 or step S304, obtaining the homomorphic encryption public key corresponding to the user in the distributed storage, specifically includes the following steps:

[0145] Step S502: Determine, from the distributed storage nodes corresponding to the login authentication system, the target distributed storage nodes for storing the key fragments of the homomorphically encrypted private key corresponding to the user.

[0146] Step S504: forward the key acquisition request to each target distributed storage node to obtain the private key fragment stored on each target distributed storage node.

[0147] Step S506, combine the private key fragments stored on each target distributed storage node to obtain the homomorphically encrypted private key corresponding to the user.

[0148] In an exemplary embodiment, the above step S504 forwards the key acquisition request to each target distributed storage node to obtain the private key fragment stored on each target distributed storage node, and specifically also includes the following content: when any one of the target distributed storage nodes fails, the key acquisition request is forwarded to the distributed backup node corresponding to the failed target distributed storage node to obtain the private key fragment backed up on the distributed backup node.

[0149] In an exemplary embodiment, the login authentication method provided by the present application further includes the following contents: after the user logs in to the login authentication system, Laplace noise is added to the data uploaded by the user to the login authentication system through the terminal to obtain the data after the noise is added; and differential privacy encryption is performed on the data after the noise is added.

[0150] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0151] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG6. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store user data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a login authentication method is implemented.

[0152] Those skilled in the art will understand that the structure shown in FIG. 6 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0153] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0154] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0155] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0156] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0157] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0158] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A login authentication system, characterized in that: The login authentication system includes a login authentication module, a key management module, a data encryption module and a behavior detection module; The login authentication module is used to, upon receiving a login request sent by a user through a terminal, obtain the distributedly stored homomorphic encryption private key corresponding to the user through the key management module, and verify the second encrypted login password and the second encrypted biometric feature carried by the login request based on the homomorphic encryption private key corresponding to the user, the pre-stored first encrypted login password of the user, and the pre-stored first encrypted biometric feature of the user, and allow the user to log in to the login authentication system after the verification is passed; The data encryption module is used to encrypt the data uploaded by the user to the login authentication system through the terminal after the user logs in to the login authentication system; The behavior detection module is used to detect abnormal information on the behavior information of the user in the login authentication system after the user logs in to the login authentication system, and issue an abnormal prompt to the user if there is abnormal information in the behavior information; Among them, the terminal stores the homomorphic encryption public key corresponding to the user; the second encrypted login password is obtained by the terminal encrypting the login password input by the user based on the homomorphic encryption public key corresponding to the user; the second encrypted biometric feature is obtained by the terminal encrypting the collected biometric feature of the user based on the homomorphic encryption public key corresponding to the user.

2. The system according to claim 1, characterized in that The login authentication module is further configured to send a key generation request corresponding to the user to the key management module when receiving a registration request sent by the user; The key management module is further used to generate a homomorphic encryption private key corresponding to the user and a homomorphic encryption public key corresponding to the user in response to a key generation request corresponding to the user, and to perform distributed storage on the homomorphic encryption private key corresponding to the user and the homomorphic encryption public key corresponding to the user; The login authentication module is further configured to obtain the homomorphic encryption public key corresponding to the user through the key management module; encrypt the login password carried in the registration request based on the homomorphic encryption public key corresponding to the user to obtain the first encrypted login password, and encrypt the biometric feature carried in the registration request to obtain the first encrypted biometric feature; and store the first encrypted login password and the first encrypted biometric feature; The key management module is also used to send the homomorphic encryption public key corresponding to the user to the terminal after the login authentication module stores the first encrypted login password and the first encrypted biometric feature.

3. The system according to claim 2, characterized in that The login authentication module is further configured to send a private key acquisition request corresponding to the user to the key management module when it is necessary to obtain the homomorphic encryption private key corresponding to the user through the key management module; The key management module is further used to determine, in response to the key acquisition request, from the distributed storage nodes corresponding to the login authentication system, the target distributed storage nodes for storing the key fragments of the homomorphically encrypted private key corresponding to the user; The key acquisition request is forwarded to each target distributed storage node to obtain the private key fragments stored on each target distributed storage node; the private key fragments stored on each target distributed storage node are combined to obtain the homomorphically encrypted private key corresponding to the user; and the homomorphically encrypted private key corresponding to the user is fed back to the login authentication module.

4. The system according to claim 3, characterized in that The key management module is also used to forward the key acquisition request to the distributed backup node corresponding to the failed target distributed storage node when any one of the target distributed storage nodes fails, so as to obtain the private key fragment backed up on the distributed backup node.

5. The system according to claim 1, characterized in that The login authentication module is also used to encrypt the verification result of the second encrypted login password and the second encrypted biometric feature based on the homomorphic encryption private key corresponding to the user, obtain the encrypted verification result, and send the encrypted verification result to the terminal; the terminal is used to decrypt the encrypted verification result based on the homomorphic encryption public key corresponding to the user, and log in to the login authentication system when the verification result obtained by decryption is verification passed.

6. The system according to any one of claims 1 to 5, characterized in that: The data encryption module is further used to add Laplace noise to the data uploaded by the user to the login authentication system through the terminal after the user logs in to the login authentication system, so as to obtain the data after the noise is added; The data to which the noise is added is subjected to differential privacy encryption processing.

7. A login authentication method, characterized in that: Applied to the login authentication system according to any one of claims 1 to 6, the method comprises: Upon receiving a login request sent by a user through a terminal, obtaining a homomorphic encryption private key corresponding to the user in distributed storage, and verifying the second encrypted login password and the second encrypted biometric feature carried by the login request based on the homomorphic encryption private key corresponding to the user, the pre-stored first encrypted login password of the user, and the pre-stored first encrypted biometric feature of the user, and allowing the user to log in to the login authentication system after the verification is passed; After the user logs in to the login authentication system, encrypt the data uploaded by the user to the login authentication system through the terminal, and perform behavior detection on the user's behavior under the login authentication system, and issue an abnormal prompt to the user if there is abnormal behavior in the behavior; Among them, the terminal stores the homomorphic encryption public key corresponding to the user; the second encrypted login password is obtained by the terminal encrypting the login password input by the user based on the homomorphic encryption public key corresponding to the user; the second encrypted biometric feature is obtained by the terminal encrypting the collected biometric feature of the user based on the homomorphic encryption public key corresponding to the user.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to claim 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claim 7 are implemented.