Two-factor identity authentication method and system based on password and key resonance biological characteristics

Abstract

The invention discloses a two-factor identity authentication method and system based on password and key resonance biological characteristics, and the method comprises the steps: obtaining password information inputted by a registered user in a registration stage, obtaining the key resonance biological characteristics when the registered user inputs the password information, and training a biological characteristic authentication model through the key resonance biological characteristics; in the login stage, password information input by a login user is obtained, key resonance biological characteristics when the login user inputs the password information are obtained, the password information in the login stage is matched with the password information in the registration stage, and if matching succeeds, the key resonance biological characteristics in the login stage are input into the trained biological characteristic authentication model; and obtaining an authentication result. According to the method, the key resonance biological characteristics generated in the password input process of the user are collected and analyzed, and the traditional password verification is combined, so that high-safety identity authentication is realized.

Description

Technical Field

[0001] The present invention relates to user authentication and authorization technology, and in particular to a two-factor identity authentication method and system based on password and key resonance biometrics. Background Art

[0002] The Internet of Things is a highly integrated and comprehensive application of information technology. It is a global intelligent network that connects objects and people. The purpose is to achieve the integration of data collected by physical devices and various sensors without human interference, so as to complete the observation and cognition of the outside world, and to form a connection with the Internet according to the rules established in the network to complete the initial state of information. With the continuous expansion of the power grid, in the context of the application of the Internet of Things, more distribution terminals need to be connected to the power grid, and operators need to perform regular maintenance to ensure the safe and stable operation of the power grid. The most important thing for operators to regularly maintain the distribution network is identity authentication. If the identity authentication is incorrect, it will lead to illegal operators accessing the distribution terminal, which may bring greater security risks to the power grid and affect the stable operation of the power grid. Identity authentication is an important part of the service architecture. In order to ensure the security of the terminal operating system, we need to establish a reliable user identification system.

[0003] Two-factor authentication requires users to provide two separate credentials for user authentication. The first factor (credential) is usually a knowledge factor, where a password or PIN is something that only a legitimate user should know. The second factor (credential) is usually a possession factor, where a hardware token (such as an ID card, USB token, and wireless tag) or a software token (such as a smartphone or smartwatch) is something that only a legitimate user should have. Hardware token-based authentication requires each legitimate user to own and carry an additional micro device, and the user needs to enter a real-time code on the device to complete the verification when logging in, which incurs high costs for the production of the device. Software token-based authentication requires the service provider to send a verification code to the user when logging in, and the user then enters it to complete the verification, which is not burden-free for the user. It can be seen that traditional solutions are costly, require user interaction, and are not compatible with the power grid environment.

[0004] In recent years, the research and application of two-factor authentication schemes for legitimate users have developed rapidly. It is no longer limited to the traditional hardware token and SMS verification code methods, and has explored authentication schemes with lower costs and simpler user interactions. The most widely used are one-click authentication and short-range communication. When a user logs in, the system will notify the user through the application and prompt the user to approve or reject the request. However, if the attacker and the operator log in to the distribution network account at the same time, the operator cannot distinguish whether the login request sent to his registered phone is legitimate, and may mistakenly approve the login request sent by the attacker. Short-range communication relies on Bluetooth low energy technology to authenticate users through Bluetooth communication between the registered mobile phone and the nearby login computer, but most browsers do not support Bluetooth API, and if the adversary sets up a Bluetooth connection with the victim's mobile phone to bypass 2FA, it will bring security risks. Therefore, how to propose an identity authentication scheme that can take into account both usability and security under the premise of reducing costs and maintaining user convenience in the context of the power grid is still a difficult problem to be solved. Summary of the invention

[0005] The technical problem to be solved by the present invention is as follows: In view of the above-mentioned problems in the prior art, a two-factor identity authentication method and system based on password and key resonance biometrics are provided, which realizes high-security identity authentication by collecting and analyzing the key resonance biometrics generated by the user in the process of entering the password and combining it with traditional password verification.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: A two-factor identity authentication method based on password and key resonance biometrics, comprising the following steps: Obtaining the first password information input by the registered user, and obtaining the first key resonance biometric feature when the registered user enters the first password information, and using the first key resonance biometric feature to train a biometric authentication model to learn a mapping relationship between the key resonance biometric feature and the user identity; Obtain the second password information entered by the logged-in user, match the second password information with the first password information, if the match is successful, obtain the second key resonance biometric feature when the logged-in user enters the second password information, input the second key resonance biometric feature into the trained biometric authentication model, and obtain the authentication result.

[0007] Furthermore, obtaining the first key resonance biometric feature when the registered user enters the first password information, and obtaining the second key resonance biometric feature when the logged-in user enters the second password information, both include: Acquire the sound signal of each key press when entering the password information, and record the timestamp of each key press to obtain the time domain signal of the sound signal of each key press; Performing noise reduction processing on the time domain signal of the sound signal of each key, and then performing Fourier transform on the time domain signal of the sound signal of each key after the noise reduction processing to obtain the frequency domain signal of the sound signal of each key; The time domain features in the time domain signal of the sound signal of each key are combined with the frequency domain features in the frequency domain signal to serve as the key resonance biometric data of each key.

[0008] Furthermore, when the time domain signal of the sound signal of each key is subjected to noise reduction processing, the signal is smoothed by a Gaussian filter to eliminate high-frequency noise, and then the signal is processed by wavelet transform to remove useless high-frequency noise.

[0009] Further, when the first key resonance biometric feature is used to train the biometric authentication model, it includes: Using the password character corresponding to the first key resonance biometric data as a label of the first key resonance biometric data, obtaining a data sample of the first key resonance biometric data, and using a GAN network to generate an adversarial sample; Dividing the data sample into a training set and a test set, adding the adversarial sample to the training set to obtain an extended training set, and using the extended training set to train a biometric authentication model to enhance generalization; The trained biometric authentication model is tested using the test set. If the biometric authentication model fails the test, the biometric authentication model is trained again using the expanded training set, and the trained biometric authentication model is tested using the test set until the biometric authentication model passes the test.

[0010] Furthermore, the biometric authentication model includes a parallel LSTM network and an FCN network. The data of the input layer of the biometric authentication model passes through multiple hidden layers and pooling layers of the FCN network in sequence to obtain first output data. The data of the input layer of the biometric authentication model passes through the LSTM layer, attention mechanism and Dropout layer of the LSTM network in sequence to obtain second output data. After the first output data and the second output data are fused, they are classified by Sigmoid function or Softmax function at the output layer of the biometric authentication model.

[0011] Furthermore, after inputting the second key resonance biometric feature into the trained biometric authentication model and obtaining the authentication result, it also includes: retraining the biometric authentication model with the authenticated second key resonance biometric feature and the first key resonance biometric feature to improve the accuracy of the biometric authentication model.

[0012] The present invention also proposes a two-factor identity authentication system based on password and key resonance biometrics, including a password input device and a server, wherein: The password input device is used to obtain the first password information input by the registered user, and register the first key resonance biometric feature when the user enters the first password information through the built-in microphone, and send the first password information and the first key resonance biometric feature to the server; The server is used to obtain the first password information and the first key resonance biometric feature and save them, and then use the first key resonance biometric feature to train the biometric authentication model to learn the mapping relationship between the key resonance biometric feature and the user identity; The password input device is also used to obtain the second password information input by the logged-in user, and obtain the second key resonance biometric feature when the logged-in user enters the second password information through the built-in microphone, and send the second password information and the second key resonance biometric feature to the server; The server is also used to obtain the second password information entered by the logged-in user, match the second password information with the first password information, and if the match is successful, obtain the second key resonance biometric feature when the logged-in user enters the second password information, input the second key resonance biometric feature into the trained biometric authentication model, and obtain the authentication result.

[0013] The present invention also proposes a two-factor identity authentication device based on password and key resonance biometrics, including a memory, a processor and a computer program stored in the memory, and the processor executes the computer program to implement any step of the two-factor identity authentication method based on password and key resonance biometrics. The present invention also proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the two-factor identity authentication methods based on password and key resonance biometrics are implemented. The present invention also proposes a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the two-factor identity authentication methods based on password and key resonance biometrics.

[0014] Compared with the prior art, the advantages of the present invention are: The present invention combines password verification and key resonance biometric verification. Even if the password is leaked, the key resonance biometric can still effectively prevent illegal login, because each person's body structure is different, and the resonance feedback of fingers and keyboards is also different.

[0015] The present invention does not require the use of any additional plug-ins or external hardware, is compatible with all computer devices with built-in microphones, and supports browsers and password login functions, and can be highly adapted to the power grid environment and easily deployed. The present invention collects the resonant sound signal generated when the user presses a key through the built-in microphone of the password input device, does not require the user to interact with devices other than the password input device, and can complete identity authentication based only on the built-in microphone of the password input device, and the authentication process is convenient and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The figure is a flow chart of a method according to an embodiment of the present invention.

[0017] Figure 2 The network framework diagram of the biometric authentication model in the embodiment of the present invention. DETAILED DESCRIPTION

[0018] The present invention is further described below in conjunction with the accompanying drawings and specific preferred embodiments, but the protection scope of the present invention is not limited thereby.

[0019] Before introducing the specific embodiments of the present invention, related concepts or terms are first explained.

[0020] Key resonance biometrics: Key resonance biometrics are based on the changes in the weak sound waveform generated when the user presses a key. They are extracted through spectrum analysis and time domain analysis and are used to distinguish the biometrics of different users.

[0021] Embodiment 1 This embodiment proposes a two-factor identity authentication method based on a password and key resonance biometrics, which implements the authentication of legitimate users in a power grid environment based on key resonance biometrics. Figure 1 As shown, there are two stages, including the registration stage and the login stage, in which: The registration phase includes the following steps: S101) The registered user enters a valid password, which is referred to as the first password in this embodiment for distinction; S102) obtaining the first password information input by the registered user, and obtaining the key resonance biometric feature when the registered user enters the first password information, which is referred to as the first key resonance biometric feature in this embodiment for distinction; S103) using the corresponding password character as a label of the first key resonance biometric feature, thereby obtaining a data sample; S104) Generate adversarial samples using GAN network; S105) training a biometric authentication model by combining the adversarial sample with the data sample of the first key resonance biometric feature to learn the mapping relationship between the key resonance biometric feature and the user identity; The landing phase includes the following steps: S201) The logged-in user enters a password, which is referred to as a second password in this embodiment for distinction; S202) obtaining the second password information input by the login user, matching the second password information with the first password information, and if the match fails, denying the login user login; S203) If the match is successful, obtain the key resonance biometric feature when the login user enters the second password information, which is called the second key resonance biometric feature in this embodiment for distinction, input the second key resonance biometric feature into the trained biometric authentication model to obtain an authentication result; if the authentication result is authentication passed, the login user is allowed to log in; if the authentication result is authentication failed, the login user is denied login.

[0022] Each step is described below.

[0023] In step S101 of this embodiment, when the registered user inputs a valid password, specifically, the registered user inputs a valid first password on a registration interface of a computer.

[0024] In step S102 of this embodiment, when the user enters the first password, not only the information of each key pressed by the user is recorded, but also the sound signal generated by the key presses when the user enters the first password is collected through the microphone of the computer. These sound signals are formed by the interaction between the resonance effect generated when the finger presses the keyboard and the air. Each time a key is pressed, the timestamp of the key press is also recorded. , according to these timestamps, the time domain signal and the frequency domain signal of the sound signal are generated to extract the key resonance biometric feature. Specifically, when obtaining the key first resonance feature when the registered user enters the first password information, it includes: S1021) Acquire the sound signal of each key press when inputting password information, and record the timestamp of each key press to obtain the time domain signal of the sound signal of each key press; S1022) performing noise reduction processing on the time domain signal of the sound signal of each key, which in this embodiment specifically includes: The signal is smoothed by a Gaussian filter to eliminate high-frequency noise. The Gaussian filter formula is:

[0025] in, is the signal at the i-th moment in the input signal, is a Gaussian function; Then use wavelet transform to process the signal and remove useless high-frequency noise. Wavelet transform can effectively remove useless high-frequency noise. After wavelet decomposition, select appropriate low-frequency coefficients to filter out high-frequency noise, thereby retaining useful signal features; S1023) Perform Fourier transform on the time domain signal of the sound signal of each key after noise reduction processing to obtain the frequency domain signal of the sound signal of each key. This embodiment converts the time domain sound signal into a frequency domain signal through Fourier transform to extract the frequency components. These frequency components contain the characteristics of the resonance between the key and the finger, and the expression is as follows:

[0026] in, is the original signal, is the corresponding frequency domain signal, is the frequency; S1024) respectively combining the time domain features in the time domain signal of the sound signal of each key with the frequency domain features in the frequency domain signal, and using the combined features (such as frequency, amplitude, duration, etc.) as the key resonance biometric data of each key In step S103 of this embodiment, the corresponding password characters are used as labels of the first key resonance biometric data, so that the first key resonance biometric data and the corresponding labels constitute a data sample corresponding to the registered user.

[0027] In this embodiment, the key resonance biometric data and password information of the registration phase are obtained through step S102 and step S103. Before step S104, the key resonance biometric data and password information of the registration phase need to be stored together as reference data for subsequent identity authentication.

[0028] In step S104 of this embodiment, the GAN network consists of a generator and a discriminator. The generator generates samples simulating the biometric characteristics of legitimate user keystroke resonance based on random noise, and the discriminator distinguishes the generated samples from the real samples through a deep convolutional network. During training, the generator is continuously optimized to generate realistic adversarial samples, while the discriminator improves the ability to distinguish between real and forged samples. The adversarial samples finally generated are used to expand the data set.

[0029] In step S105 of this embodiment, based on a certain amount of data samples obtained in step S102 and step S103, a deep learning model is trained using the data therein. During the training process, the model learns the mapping relationship between the key resonance biometrics extracted from the sound signal and the user identity, thereby identifying the personalized resonance features when the user inputs. In order to enhance the generalization of the model, the adversarial samples generated by the GAN network in step S104 are used in the training phase to jointly train the model with the actual samples, thereby enhancing the generalization of the model and the ability to identify illegal users.

[0030] In this embodiment, the deep learning model adopts the LSTM+FCN biometric authentication model, such as Figure 2As shown in the figure, the model includes parallel LSTM networks and FCN networks, which are responsible for extracting information from the input password key resonance biometrics and classifying legitimate and illegitimate users. The FCN network consists of multiple hidden layers and a pooling layer. The data of the input layer of the biometric authentication model passes through multiple hidden layers and pooling layers of the FCN network in sequence to obtain the first output data. In this process, the hidden layer processes the input features through nonlinear activation functions (such as ReLU) to learn the subtle patterns of user input and help the network distinguish the feature differences between legitimate users and illegal users. The pooling layer maps the features of the hidden layer output to a fixed-length vector through global maximum pooling, which can effectively capture global information.

[0031] The LSTM network includes an LSTM layer, an attention mechanism, and a Dropout layer. The input layer data of the biometric authentication model passes through the LSTM layer, the attention mechanism, and the Dropout layer of the LSTM network in turn to obtain the second output data. In this process, the hidden state of each time step of the input data is calculated through the LSTM layer, and then the attention mechanism is input to re-weight the hidden state of each time step, and the attention mechanism is applied to focus on important time step features. Finally, dropout is applied to the output of the attention mechanism through the Dropout layer to prevent overfitting.

[0032] After the first output data and the second output data are fused, the user is classified as legal or illegal through binary classification (using Sigmoid or Softmax) at the output layer of the biometric authentication model, and the output is a probability value indicating the legitimacy of the user's identity.

[0033] The LSTM+FCN biometric authentication model combines the feature extraction process of LSTM and FCN to capture the temporal dependency and local features of the data, thereby enhancing the model's feature recognition ability. The introduction of the attention mechanism and dropout further improves the model's attention and generalization capabilities. In step S105 of this embodiment, when training the biometric authentication model by combining the adversarial sample with the data sample of the first key resonance biometric feature, it includes: Dividing the data samples of the first resonance feature into a training set and a test set. In this embodiment, the training set and the test set are divided according to the historical login data. The training set is used to train the biometric authentication model, and the test set is used to verify the accuracy of the biometric authentication model. Obtain adversarial samples generated by the GAN network, add the adversarial samples to the training set to obtain an extended training set, and use the extended training set to train the biometric authentication model to enhance generalization. In the process of using the extended training set to train the biometric authentication model, update the generator of the GAN network in each training cycle to generate more diverse adversarial samples, and use the adversarial samples generated by the updated generator to update the extended training set. The trained biometric authentication model is tested using the test set. If the biometric authentication model fails the test, the biometric authentication model is trained again using the expanded training set, and the trained biometric authentication model is tested using the test set until the biometric authentication model passes the test.

[0034] In this embodiment, when the adversarial sample and the data sample of the first key resonance biometric feature are combined to train the biometric authentication model, the goal of the model training is to minimize the loss function, and the typical loss function is the binary cross-extraction loss:

[0035] in, is the probability predicted by the model, is the actual label (1 for a valid user, 0 for an invalid user). After training, we get a validated biometric authentication model that can distinguish between valid and invalid users.

[0036] In step S201 of this embodiment, when the logged-in user enters the password, specifically, the logged-in user enters the second password on the login interface of the computer.

[0037] In step S202 of this embodiment, when the user enters the second password, not only is the information of each key pressed by the user recorded, but also the sound signal generated by the key presses when the user enters the second password is collected through the microphone built into the computer. Each time a key is pressed, the timestamp of the key press is also recorded. .

[0038] In step S203 of this embodiment, the key resonance biometric feature obtained when the logged-in user enters the second password information is the same as the key resonance biometric feature obtained when the registered user enters the first password information. First, the time domain signal of the sound signal is generated according to these timestamps, and the time domain signal of the sound signal is preprocessed (Gaussian filtering, wavelet noise reduction), and then the frequency domain signal is obtained through Fourier transform, and finally the key resonance biometric feature is extracted by combining the time domain features in the time domain signal with the frequency domain features in the frequency domain signal.

[0039] In step S203 of this embodiment, when the second key resonance biometric feature is input into the trained biometric authentication model, the biometric authentication model calculates the predicted probability of a legitimate user based on the input key resonance biometric feature data. If the classification result is a legitimate user (i.e., the output is 1), the user is allowed to log in; otherwise, if it is an illegal user (i.e., the output is 0), the login is denied and the operation is recorded.

[0040] In order to improve the authentication accuracy of the biometric authentication model, in this embodiment, after step S203, it also includes: obtaining the second key resonance biometric feature of the user whose authentication is passed, that is, the classification result is a legitimate user, combining the obtained second key resonance biometric feature and the first key resonance biometric feature into a new data sample, and training the biometric authentication model again. Similarly, adversarial samples generated by the GAN network are added during the training process to enhance the generalization of the model.

[0041] Embodiment 2 This embodiment proposes a two-factor identity authentication system based on a password and a key resonance biometric feature, including a password input device and a server, wherein: The password input device is used to obtain the first password information input by the registered user, and register the first key resonance biometric feature when the user enters the first password information through the built-in microphone, and send the first password information and the first key resonance biometric feature to the server; The server is used to obtain the first password information and the first key resonance biometric feature and save them, and then use the first key resonance biometric feature to train the biometric authentication model to learn the mapping relationship between the key resonance biometric feature and the user identity; The password input device is also used to obtain the second password information input by the logged-in user, and obtain the second key resonance biometric feature when the logged-in user enters the second password information through the built-in microphone, and send the second password information and the second key resonance biometric feature to the server; The server is also used to obtain the second password information and then match the second password information with the first password information. If the match is unsuccessful, the login user is denied login; if the match is successful, the second key resonance biometric feature is obtained and the second key resonance biometric feature is input into the trained biometric authentication model to obtain an authentication result; if the authentication result is authentication passed, the login user is allowed to log in; if the authentication result is authentication failed, the login user is denied login.

[0042] Embodiment 3 This embodiment proposes a two-factor identity authentication device based on a password and a key resonance biometric feature, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of the two-factor identity authentication method based on a password and a key resonance biometric feature described in Embodiment 1. This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the two-factor identity authentication method based on password and key resonance biometrics described in the first embodiment are implemented. This embodiment further proposes a computer program product, including a computer program, which, when executed by a processor, implements the steps of the two-factor identity authentication method based on password and key resonance biometrics described in the first embodiment.

[0043] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A two-factor identity authentication method based on password and key resonance biometrics, characterized in that: The following steps are involved: Obtaining the first password information input by the registered user, and obtaining the first key resonance biometric feature when the registered user enters the first password information, and using the first key resonance biometric feature to train a biometric authentication model to learn a mapping relationship between the key resonance biometric feature and the user identity; Obtain the second password information entered by the logged-in user, match the second password information with the first password information, if the match is successful, obtain the second key resonance biometric feature when the logged-in user enters the second password information, input the second key resonance biometric feature into the trained biometric authentication model, and obtain the authentication result.

2. The two-factor identity authentication method based on password and key resonance biometrics according to claim 1 is characterized in that: Acquiring the first key resonance biometric feature when the registered user enters the first password information, and acquiring the second key resonance biometric feature when the logged-in user enters the second password information, both include: Acquire the sound signal of each key press when entering the password information, and record the timestamp of each key press to obtain the time domain signal of the sound signal of each key press; Performing noise reduction processing on the time domain signal of the sound signal of each key, and then performing Fourier transform on the time domain signal of the sound signal of each key after the noise reduction processing to obtain the frequency domain signal of the sound signal of each key; The time domain features in the time domain signal of the sound signal of each key are combined with the frequency domain features in the frequency domain signal to serve as the key resonance biometric data of each key.

3. The two-factor identity authentication method based on password and key resonance biometrics according to claim 2 is characterized in that: When the time domain signal of the sound signal of each key is subjected to noise reduction processing, the signal is smoothed by a Gaussian filter to eliminate high-frequency noise, and then the signal is processed by a wavelet transform to remove useless high-frequency noise.

4. The two-factor identity authentication method based on password and key resonance biometrics according to claim 1 is characterized in that: When training a biometric authentication model using the first key resonance biometric, include: Using the password character corresponding to the first key resonance biometric data as a label of the first key resonance biometric data, obtaining a data sample of the first key resonance biometric data, and using a GAN network to generate an adversarial sample; Dividing the data sample into a training set and a test set, adding the adversarial sample to the training set to obtain an extended training set, and using the extended training set to train a biometric authentication model to enhance generalization; The trained biometric authentication model is tested using the test set. If the biometric authentication model fails the test, the biometric authentication model is trained again using the expanded training set, and the trained biometric authentication model is tested using the test set until the biometric authentication model passes the test.

5. The two-factor identity authentication method based on password and key resonance biometrics according to claim 1, characterized in that: The biometric authentication model includes a parallel LSTM network and an FCN network. The data of the input layer of the biometric authentication model passes through multiple hidden layers and pooling layers of the FCN network in sequence to obtain first output data. The data of the input layer of the biometric authentication model passes through the LSTM layer, attention mechanism and Dropout layer of the LSTM network in sequence to obtain second output data. After the first output data and the second output data are fused, they are classified by Sigmoid function or Softmax function at the output layer of the biometric authentication model.

6. The two-factor identity authentication method based on password and key resonance biometrics according to claim 1 is characterized in that: After inputting the second key resonance biometric feature into the trained biometric authentication model and obtaining the authentication result, it also includes: re-training the biometric authentication model with the authenticated second key resonance biometric feature and the first key resonance biometric feature to improve the accuracy of the biometric authentication model.

7. A two-factor identity authentication system based on password and key resonance biometrics, characterized in that: The invention comprises a password input device and a server, wherein: The password input device is used to obtain the first password information input by the registered user, and register the first key resonance biometric feature when the user enters the first password information through the built-in microphone, and send the first password information and the first key resonance biometric feature to the server; The server is used to obtain the first password information and the first key resonance biometric feature and save them, and then use the first key resonance biometric feature to train the biometric authentication model to learn the mapping relationship between the key resonance biometric feature and the user identity; The password input device is also used to obtain the second password information input by the logged-in user, and obtain the second key resonance biometric feature when the logged-in user enters the second password information through the built-in microphone, and send the second password information and the second key resonance biometric feature to the server; The server is also used to obtain the second password information entered by the logged-in user, match the second password information with the first password information, and if the match is successful, obtain the second key resonance biometric feature when the logged-in user enters the second password information, input the second key resonance biometric feature into the trained biometric authentication model, and obtain the authentication result.

8. A two-factor identity authentication device based on password and key resonance biometrics, comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the two-factor identity authentication method based on password and key resonance biometrics as described in any one of claims 1 to 6.

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 two-factor identity authentication method based on password and key resonance biometrics as described in any one of claims 1 to 6 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 two-factor identity authentication method based on password and key resonance biometrics as described in any one of claims 1 to 6 are implemented.

Images