Bidirectional trusted identity verification method and system based on offline file

Abstract

The invention discloses a bidirectional trusted identity authentication method and system based on an offline file, and particularly relates to the technical field of authentication, comprising the steps of evaluating the randomness of a key based on the entropy value of the calculated key, analyzing key entropies at different time points, obtaining random data, and obtaining the random data based on the error rate occurring in the calculation transmission process. The method comprises the following steps: indirectly evaluating the validity and security of encrypted transmission, acquiring intensity data, quantifying the security of bidirectional trusted identity verification in a multi-point transmission scene within a time range, generating similar data based on comparing historical data of a receiving node with characteristics of a current transmission file, analyzing response time of a transmission process, generating performance data, and performing encryption and decryption on the received data. According to the method, the credibility of the transmission process is evaluated, quantitative results of the safety and the credibility in the transmission process serve as input of a neural network, a model is trained to predict potential abnormal conditions, and the method is beneficial to ensuring that the identities of the two parties are credible in the transmission process and carrying out timely early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of software development, and more specifically, to a two-way trusted identity authentication method and system based on offline files. Background Art

[0002] When performing two-way trusted identity authentication based on offline files, the transmission nodes of the two communicating parties establish a mutual trust relationship based on digital certificates, pre-shared keys, etc. After such identity authentication is successful, file transmission begins between the nodes. Multi-point transmission technology is used during the file transmission process. To ensure the security of file transmission and prevent potential attacks and data leakage, different transmission points usually use different keys for encryption to increase transmission security, and the keys are updated regularly. Although existing identity authentication methods can still effectively ensure data security in some scenarios, traditional methods are usually lagging behind in anomaly detection and response, failing to issue timely alerts to potential security threats, increasing the risk of data leakage and security incidents, and it is not easy to fully evaluate the security and reliability of data transmission during identity authentication.

[0003] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a two-way trusted identity authentication method and system based on offline files to solve the problem that it is not easy to fully evaluate the security and reliability of data transmission during identity authentication.

[0005] To achieve the above object, the present invention provides the following technical solutions: The method for two-way trusted identity authentication based on offline files specifically includes the following steps: evaluating the randomness of a key based on the calculated entropy value of the key, analyzing the key entropy at different time points, obtaining randomness data, indirectly evaluating the effectiveness and security of encrypted transmission based on the bit error rate occurring during the calculated transmission process, and obtaining strength data; performing data analysis on the randomness data and the strength data, and quantifying the security of two-way trusted identity authentication in a multi-point transmission scenario within a time range; generating similar data based on comparing the historical data of the receiving node and the characteristics of the currently transmitted file, analyzing the response time of the transmission process, generating performance data, and evaluating the trust of the transmission process; using the quantified results of security and trust during the transmission process as input to the neural network, and training the model to predict potential abnormal situations.

[0006] In a preferred embodiment, randomness data, intensity data, similarity data and performance data include: representing randomness data and intensity data based on randomness fluctuation coefficient of variation and intensity hidden risk coefficient, respectively; representing similarity data and performance data based on similarity anomaly coefficient and total response anomaly coefficient.

[0007] In a preferred embodiment, randomness data includes: the method for obtaining the randomness fluctuation coefficient of variation is: obtaining the size of the key entropy at different nodes at the same time; setting a monitoring interval, obtaining the size of the key entropy at the nodes at different times in the monitoring interval, and marking the size of the key entropy at the nodes at different times in the monitoring interval; calculating the average value and standard deviation of the key entropy at the nodes at different times, marking the average value and standard deviation of the key entropy at the nodes at different times to calculate the coefficient of variation of the key entropy at the nodes at different times; calculating the randomness fluctuation coefficient of variation.

[0008] In a preferred embodiment, the intensity data includes: the method for obtaining the intensity concealment risk coefficient is: based on real-time monitoring of data transmission, obtaining the bit error rates of different nodes at different times in the monitoring interval, and marking the bit error rates of different nodes at different times in the monitoring interval; Set the bit error rate threshold, mark the bit error rate threshold, compare the bit error rate of different nodes at different times in the monitoring interval with the bit error rate threshold, mark the bit error rate of nodes with a bit error rate greater than the bit error rate threshold at different times in the monitoring interval; calculate the intensity concealment risk coefficient.

[0009] In a preferred embodiment, the security of two-way trusted identity authentication in a multi-point transmission scenario within a time range is quantified, including: weighted calculation of the random fluctuation coefficient of variation and the intensity concealment risk coefficient, constructing a transmission security assessment model, and generating a security assessment coefficient.

[0010] In a preferred embodiment, the similarity data includes: the method for obtaining the similarity anomaly coefficient is: extracting features from offline files, and converting the features extracted from offline files into set A, extracting features from each node, and converting the features extracted from each node into set ; Calculate the similarity anomaly coefficient based on Jaccard similarity.

[0011] In a preferred embodiment, the performance data includes: the method for obtaining the total response anomaly coefficient is: dividing the monitoring interval into an actual prediction time interval and a training time interval, obtaining the response time of different nodes receiving offline file data packets in the training time interval, and marking the response time of different nodes receiving offline file data packets in the training time interval; using the data in the training time interval to establish an autoregressive model; obtaining the response time of different nodes receiving offline file data packets in the actual prediction time interval, marking the response time of different nodes receiving offline file data packets in the actual prediction time interval, obtaining the response time of different nodes receiving offline file data packets in the actual prediction time interval predicted based on the autoregressive model, and marking the response time of different nodes receiving offline file data packets in the actual prediction time interval predicted based on the autoregressive model; calculating the response prediction anomaly coefficients of different nodes; calculating the total response anomaly coefficient.

[0012] In a preferred embodiment, predicting a potential abnormal situation includes: The safety assessment coefficients of different monitoring intervals, the trust assessment coefficients of different monitoring intervals, the number of monitoring intervals and the time length of the monitoring intervals are used as the input of the neural network model training, and the verification warning coefficient is used as the output of the neural network model training, and it is assigned to 0 or 1 to train the model, where 0 indicates that the verification warning coefficient is less than the verification warning coefficient threshold, and 1 indicates that the verification warning coefficient is greater than the verification warning coefficient threshold.

[0013] In a preferred embodiment, a two-way trusted identity authentication system based on offline files includes a data acquisition module, a data analysis module, a security assessment module, a trust assessment module and a neural network early warning module, and the modules are signal-connected; the data acquisition module is used to collect relevant data from the transmission process, including key entropy value, bit error rate, response time of the data packet, characteristic data of the receiving node and characteristic data of the transmitted file; the data analysis module is used to analyze and process the collected data, including entropy value analysis, bit error rate calculation, response time analysis, and characteristic value comparison; the security assessment module is used to perform data analysis based on randomness data and strength data to evaluate the security of the entire transmission process; the trust assessment module is used to perform data analysis based on similarity data and performance data to evaluate the trust of the transmission process; the neural network early warning module is used to use a trained neural network model to monitor the transmission process in real time and predict potential abnormal situations.

[0014] Technical effects and advantages of the present invention: The present invention analyzes the transmission process of offline files in a multi-point transmission scenario, evaluates the randomness of the key based on the key entropy, measures the randomness strength at different times, and indirectly reflects the effectiveness and security of the encrypted transmission based on the bit error rate. The security of the transmission process is analyzed from an overall perspective, and the trust of the transmission process is determined based on the similarity between the offline file and the receiving node, as well as the response time of the transmission process. The offline file transmission process is warned based on the construction of a neural network model, which helps to ensure that the identities of both parties are credible during the transmission process and to issue timely warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings; Figure 1 It is a flow chart of the two-way trusted identity authentication method based on offline files of the present invention; Figure 2 It is a structural schematic diagram of the two-way trusted identity authentication system based on offline files of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example 1 Figure 1 A schematic flow chart of a two-way trusted identity authentication method based on offline files of the present invention is provided, which specifically includes the following steps: S1: Evaluate the randomness of the key based on the calculated entropy value of the key, analyze the key entropy at different time points, obtain randomness data, and indirectly evaluate the effectiveness and security of encrypted transmission based on the bit error rate that occurs during the calculation of the transmission process to obtain strength data; S2: Perform data analysis on randomness data and strength data to quantify the security of two-way trusted authentication in multi-point transmission scenarios within a time range; S3: Generate similar data based on comparing the historical data of the receiving node and the characteristics of the current transmitted file, analyze the response time of the transmission process, generate performance data, and evaluate the trust of the transmission process; S4: The quantified results of security and trust during transmission are used as input to the neural network to train the model to predict potential abnormal situations.

[0018] In the multi-point transmission scenario, when performing two-way trusted identity authentication, the transmission nodes of both parties are determined. The nodes have known and trusted each other based on a certain mechanism (such as certificates, pre-shared keys, etc.). After successful verification, the security of the transmission process is monitored during the file transfer process. To ensure the security of data transmission and prevent possible attacks or data leakage, the keys of different transmission points are different and updated regularly, including: Use different keys to ensure the independence of data flows between different points, so that communications at other points are not affected when the key of one point is attacked or leaked. Key updates at different points may not be completely synchronized, especially if the security requirements of these points are different. For example, some highly sensitive transmission nodes may require more frequent key updates, while other nodes may have a longer key lifecycle. An independent encryption channel is usually established between each two transmission points, that is, different keys are used between each node. Multi-point transmission uses quantum key distribution (QKD) technology. The generation of quantum keys is based on uncertainty and the non-replicability of quantum states. The keys generated between different nodes are independent and random. The keys at different transmission points are unique and are updated regularly or destroyed after the session ends. In multi-point transmission, the key management system (KMS) is responsible for generating, distributing, and updating keys between different points. KMS ensures that the keys used by each point at different times or in different sessions are independent and secure. KMS tracks the life cycle of the keys to ensure regular updates or rotation when the keys are leaked. In multi-point transmission, commonly used encryption protocols (such as TLS, IPsec, etc.) support key negotiation mechanisms. Even in multi-point transmission, each point will negotiate an independent session key with other points before communication; Multipoint transmission can be encrypted based on different transmission layers, such as application layer, network layer or link layer, and each layer of encryption uses different keys.

[0019] During the process of two-way trusted identity authentication of offline files, if the key generation process is interfered with or eavesdropped by an attacker, the randomness of the key may decrease, and the strength of the encryption algorithm may decrease. The randomness of the key is evaluated based on the key entropy to obtain randomness data, and the strength data is obtained based on the strength of the encryption algorithm monitored. The randomness data and strength data are represented based on the randomness fluctuation coefficient of variation and the strength concealment risk coefficient, respectively.

[0020] The randomness of the key is evaluated based on the key entropy, and the randomness strength at different times is measured. Entropy is a measure of the uncertainty and unpredictability of data in the key sequence. At different time points or under different conditions, the generated key sequence may have different randomness strengths due to changes in noise, device conditions, channel conditions or other environmental factors. Based on the evaluation of the key entropy at different times, the randomness performance of the key at different time points is analyzed, thereby evaluating the stability and reliability of the key generation process.

[0021] The method for obtaining the random fluctuation coefficient of variation is: obtaining the size of the key entropy at different nodes at the same time, and marking the size of the key entropy at different nodes at the same time as: , where n=1, 2, 3, ..., N, N is a positive integer, and n is the number of keys in multi-point transmission. The key entropy at different nodes at the same time is obtained based on the Shannon entropy. The expression is: , is a specific value that the random variable x can take, and different represents different results or states, I is the total number of different values ​​that the random variable x can take, and b is usually chosen to be 2. Indicates that the random variable x takes a certain value probability; It should be noted that the relationship between the number of keys and the number of nodes depends on the specific transmission architecture and encryption protocol, which is set by professional staff and selects the appropriate key management strategy based on specific application scenarios and requirements.

[0022] Set the monitoring interval, obtain the size of the key entropy at different time nodes in the monitoring interval, and mark the size of the key entropy at different time nodes in the monitoring interval as: ; Wherein, m=1, 2, 3, ..., M, M is a positive integer, and m is the number of different moments in the monitoring interval; It should be noted that the monitoring interval is a specific length of time, which is set by professional staff and will not be elaborated here.

[0023] Calculate the mean and standard deviation of the key entropy at different time nodes, and mark the mean and standard deviation of the key entropy at different time nodes as: and ;in, , ; Calculate the coefficient of variation of the key entropy at different nodes at different times. The calculation formula is: ;in, is the coefficient of variation of the key entropy of the nth node; Calculate the random fluctuation coefficient of variation, the calculation formula is: ,in, is the coefficient of variation of random fluctuations.

[0024] It can be seen from the formula that the larger the random fluctuation coefficient of variation, the higher the volatility of the key entropy of different nodes at different times within the monitoring interval, which means that the randomness and unpredictability of the generated key or random number sequence have changed significantly within a certain period of time, which may lead to a decrease in the security of the key and make it more vulnerable to attacks.

[0025] Since the bit error rate indirectly reflects the effectiveness and security of encrypted transmission, a higher bit error rate may indicate that the transmission signal is interfered with, which may threaten the integrity of the encrypted data, meaning that under poor channel conditions, the encryption strength may decrease because erroneous data may lead to incorrect decryption results.

[0026] The method for obtaining the intensity concealment risk coefficient is: based on real-time monitoring of data transmission, the bit error rates of different nodes at different times in the monitoring interval are obtained, and the bit error rates of different nodes at different times in the monitoring interval are marked as: ,in, ;in, is the number of error bits that occur at the nth node at the mth moment, is the number of correct bits that appear in the nth node at the mth moment; Set the bit error rate threshold and mark the bit error rate threshold as: , compare the bit error rate of different nodes at different times in the monitoring interval with the bit error rate threshold, and mark the bit error rate of nodes at different times in the monitoring interval that are greater than the bit error rate threshold as: , where j=1, 2, 3, ..., J, J is a positive integer, J is the number of the node with a bit error rate greater than the threshold, k=1, 2, 3, ..., K, K is a positive integer, k is the number of the moment with a bit error rate greater than the threshold; Calculate the intensity hidden risk coefficient, the calculation formula is: ;in, The intensity concealed risk factor.

[0027] It can be seen from the formula that the greater the intensity concealment risk coefficient, the higher the bit error rate of different nodes in the monitoring interval at different times, indicating that the transmission signal may be interfered with, which may threaten the integrity of the encrypted data.

[0028] The random fluctuation coefficient of variation and the intensity hidden danger coefficient are weighted and calculated to construct a transmission safety assessment model and generate a safety assessment coefficient. The expression of the safety assessment coefficient is: ;in, is the safety assessment factor, is the proportional coefficient of the random fluctuation coefficient of variation, is the proportional coefficient of the intensity concealed hazard coefficient, and Both are greater than 0.

[0029] Based on the extracted features of offline files and the features of receiving nodes, the similarity data of offline files in the transmission process is determined using a similarity calculation method. Based on the response time of data transmission in multi-point transmission, the performance data of offline files in the transmission process is determined. The similarity data and performance data are represented based on the similarity anomaly coefficient and the total response anomaly coefficient.

[0030] Based on the features of offline files and receiving nodes, feature comparison is performed to evaluate the trust in multi-point transmission. This can be understood from the following aspects: Suitability assessment: File features include file type, size, encryption method, content sensitivity, etc. Node features include node processing capability, storage capability, security level, permission settings, etc. Matching is performed based on the same features extracted from file features and node features. If the features of the receiving node are highly matched with the features of the offline file, it means that the node is suitable for receiving the file, thereby increasing the trust level. Identify potential risks: Based on feature comparison, potential risks in the transmission process can be identified, such as the receiving node’s insufficient permissions to access sensitive files, which may lead to data leakage or unauthorized access.

[0031] The method for obtaining the similarity anomaly coefficient is as follows: extracting features from offline files and converting the features extracted from offline files into set A, extracting features from each node and converting the features extracted from each node into set ; The similarity anomaly coefficient is calculated based on Jaccard similarity. The calculation formula is: ;in, is the similarity anomaly coefficient.

[0032] It can be seen from the formula that the smaller the similarity anomaly coefficient is, the more similar the characteristics of the offline file are to those of the receiving node, which may indicate that the node can effectively process the file, thereby improving the reliability of file transmission. Conversely, if the similarity anomaly coefficient is large, it may indicate that the node is not suitable for receiving the file, thus causing security or performance issues.

[0033] Under normal circumstances, a trusted system is usually able to process requests and return responses quickly. During the authentication process, if the response time is too long, it may indicate that the system encountered problems when processing the request, or there are potential security risks (such as man-in-the-middle attacks). Therefore, in the offline file authentication method, the response time of multi-point transmission not only reflects the performance and stability of the system, but also helps identify security risks. It is an important and effective indicator for evaluating trust.

[0034] The method for obtaining the total response anomaly coefficient is as follows: the monitoring interval is divided into an actual prediction time interval and a training time interval, the response time of different nodes receiving offline file data packets in the training time interval is obtained, and the response time of different nodes receiving offline file data packets in the training time interval is marked as: , where t=1, 2, 3, ..., T, T is a positive integer, and t is the number of the response time of each data packet; It should be noted that the actual prediction time interval and the training time interval are commonly used methods in time series analysis. When using an autoregressive model, the data in the actual prediction time interval is predicted based on the data in the training time interval using the autoregressive model, and the data is compared with the data in the actual prediction time interval to evaluate the response abnormality. The division of the actual prediction time interval and the training time interval is set by professional staff.

[0035] Use the data in the training time interval to build an autoregressive model, the expression is: ;in, is the response time of the tth data packet predicted based on the autoregressive model, are the coefficients of the model, is the error term, and p is the lag term based on the data in the training time interval; The response time of receiving offline file data packets at different nodes in the actual prediction time interval is obtained, and the response time of receiving offline file data packets at different nodes in the actual prediction time interval is marked as: , obtain the response time of receiving offline file data packets at different nodes in the actual prediction time interval predicted by the autoregressive model, and mark the response time of receiving offline file data packets at different nodes in the actual prediction time interval predicted by the autoregressive model as: , where f=1, 2, 3, ..., F, F is a positive integer and f is the number of the data packet contained in the actual prediction time interval; Calculate the response prediction anomaly coefficient of different nodes, the calculation formula is: ;in, predict anomaly coefficients for the responses; Calculate the total response anomaly coefficient using the following formula: ;in, is the total response anomaly coefficient.

[0036] It can be seen from the formula that the larger the total response anomaly coefficient is, the greater the deviation between the current observed value and the predicted value is, and there may be outliers. Outliers may represent abnormal behaviors or events, such as network attacks, equipment failures, data input errors, etc., and a larger total response anomaly coefficient may indicate that the stability of the system is reduced, which may cause more uncertainties and unforeseen risks.

[0037] The similarity anomaly coefficient and the total response anomaly coefficient are calculated based on weighted calculation to construct a trust evaluation model and generate a trust evaluation coefficient. The expression of the trust evaluation coefficient is: ;in, is the trust evaluation coefficient, is the proportional coefficient of the similarity anomaly coefficient, is the proportional coefficient of the total response anomaly coefficient, and Both are greater than 0.

[0038] The safety assessment coefficients of different monitoring intervals, the trust assessment coefficients of different monitoring intervals, the number of monitoring intervals and the time length of the monitoring intervals are used as the input of the neural network model training, and the verification warning coefficient is used as the output of the neural network model training, and it is assigned to 0 or 1 to train the model, where 0 indicates that the verification warning coefficient is less than the verification warning coefficient threshold, and 1 indicates that the verification warning coefficient is greater than the verification warning coefficient threshold.

[0039] It should be noted that the setting of the verification warning coefficient threshold is used to distinguish between normal status and potential abnormal status, and determines that when the verification warning coefficient exceeds the threshold, the system should trigger an alarm or take safety measures. The setting of the verification warning coefficient threshold should be based on actual business needs and experience data, and should be set by professional staff.

[0040] Example 2 Figure 2 The present invention provides a schematic diagram of the structure of a two-way trusted identity authentication system based on offline files, including a data acquisition module, a data analysis module, a security assessment module, a trustworthiness assessment module and a neural network early warning module, and signal connections between the modules; The data collection module is used to collect relevant data from the transmission process, including key entropy value, bit error rate, response time of data packets, characteristic data of receiving nodes and characteristic data of transmitted files; Data analysis module, used to analyze and process the collected data, including entropy analysis, bit error rate calculation, response time analysis, and characteristic value comparison; The security assessment module is used to perform data analysis based on randomness data and strength data to assess the security of the entire transmission process; A trust evaluation module is used to perform data analysis based on similarity data and performance data to evaluate the trust of the transmission process; The neural network early warning module is used to use the trained neural network model to monitor the transmission process in real time and predict potential abnormal situations.

[0041] The present invention analyzes the transmission process of offline files in a multi-point transmission scenario, evaluates the randomness of the key based on the key entropy, measures the randomness strength at different times, and indirectly reflects the effectiveness and security of the encrypted transmission based on the bit error rate. The security of the transmission process is analyzed from an overall perspective, and the trust of the transmission process is determined based on the similarity between the offline file and the receiving node, as well as the response time of the transmission process. The offline file transmission process is warned based on the construction of a neural network model, which helps to ensure that the identities of both parties are credible during the transmission process and to issue timely warnings.

[0042] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0043] The above embodiments can be implemented in whole or in part based on software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center based on wired or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0044] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0045] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0046] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0047] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented based on other methods. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be based on some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0048] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0049] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A two-way trusted identity authentication method based on offline files, characterized in that: The specific steps include: Evaluate the randomness of the key based on the calculated entropy value of the key, and analyze the key entropy at different time points to obtain randomness data; Based on the bit error rate that occurs during the transmission process, the effectiveness of encrypted transmission is evaluated and strength data is obtained; The randomness data and strength data are analyzed to quantify the security of two-way trusted authentication in multi-point transmission scenarios within a time range; Generate similar data based on comparing the historical data of the receiving node and the characteristics of the current transmitted file, analyze the response time of the transmission process, generate performance data, and evaluate the trustworthiness of the transmission process; The quantified results of security and trust during the transmission process are used as input to the neural network to train the model and predict potential abnormal situations.

2. The two-way trusted identity authentication method based on offline files according to claim 1 is characterized in that: The randomness data includes the randomness fluctuation coefficient of variation; the intensity data includes the intensity hidden danger coefficient; the similarity data includes the similarity anomaly coefficient; and the performance data includes the total response anomaly coefficient.

3. The two-way trusted identity authentication method based on offline files according to claim 2 is characterized in that: The method for obtaining the random fluctuation coefficient of variation is: Obtain the size of the key entropy at different nodes at the same time, and mark the size of the key entropy at different nodes at the same time; The key entropy at different nodes at the same time is obtained based on Shannon entropy calculation; Set a monitoring interval, obtain the size of the key entropy at different time nodes in the monitoring interval, and mark the size of the key entropy at different time nodes in the monitoring interval; Calculate the average and standard deviation of the key entropy at different nodes at different times; Calculate the coefficient of variation of key entropy at different time nodes according to the mean value and standard deviation of key entropy; The coefficient of variation of randomness fluctuation is calculated based on the coefficient of variation of key entropy.

4. The method for two-way trusted identity authentication based on offline files according to claim 3 is characterized in that: The method for obtaining the intensity concealed risk coefficient is: Based on real-time monitoring of data transmission, the bit error rates of different nodes at different times within the monitoring interval are obtained, and the bit error rates of different nodes at different times within the monitoring interval are marked; Set a bit error rate threshold, compare the bit error rates of different nodes at different times in the monitoring interval with the bit error rate threshold, and mark the bit error rates of nodes at different times in the monitoring interval that are greater than the bit error rate threshold; Data analysis is performed based on the bit error rates of nodes greater than the bit error rate threshold at different times within the monitoring interval to calculate the intensity concealment risk coefficient.

5. The method for two-way trusted identity authentication based on offline files according to claim 4 is characterized in that: The method for obtaining the total response anomaly coefficient is: The monitoring interval is divided into an actual prediction time interval and a training time interval, the response time of different nodes receiving offline file data packets in the training time interval is obtained, and the response time of different nodes receiving offline file data packets in the training time interval is marked; The autoregressive model is established using the data in the training time interval to obtain the response time of different nodes receiving offline file data packets in the actual prediction time interval; Marking the response time of receiving offline file data packets at different nodes in the actual prediction time interval, obtaining the response time of receiving offline file data packets at different nodes in the actual prediction time interval predicted by the autoregressive model, and marking the response time of receiving offline file data packets at different nodes in the actual prediction time interval predicted by the autoregressive model; According to the response time of receiving offline file data packets at different nodes in the actual prediction time interval predicted by the autoregressive model, data analysis is performed to calculate the response prediction anomaly coefficients of different nodes; The total response anomaly coefficient is calculated by weighted summing up the response prediction anomaly coefficients of different nodes.

6. The method for two-way trusted identity authentication based on offline files according to claim 5 is characterized in that: The method for obtaining the similarity anomaly coefficient is: Extract features from offline files and convert them into set A, extract features from each node and convert them into set A ; Calculate the similarity anomaly coefficient based on Jaccard similarity.

7. The method for two-way trusted identity authentication based on offline files according to claim 6, characterized in that: The quantification of the security of two-way trusted identity authentication in a multi-point transmission scenario within a time range is specifically: The random fluctuation coefficient of variation and the intensity hidden danger coefficient are weighted and calculated to construct a transmission safety assessment model and generate a safety assessment coefficient; The expression of the safety assessment coefficient is: ; In the formula, is the safety assessment factor, is the proportional coefficient of the random fluctuation coefficient of variation, is the proportional coefficient of the intensity concealed hazard coefficient, and Both are greater than 0.

8. The method for two-way trusted identity authentication based on offline files according to claim 7, characterized in that: The trustworthiness of the evaluation transmission process is specifically as follows: The similarity anomaly coefficient and the total response anomaly coefficient are calculated based on weighted calculation to construct a trust evaluation model and generate a trust evaluation coefficient.

9. The method for two-way trusted identity authentication based on offline files according to claim 8, characterized in that: The predicted potential abnormal situations are specifically: The safety assessment coefficients of different monitoring intervals, the trust assessment coefficients of different monitoring intervals, the number of monitoring intervals and the time length of the monitoring intervals are used as inputs for neural network model training; The verification warning coefficient is used as the output of the neural network model training, and is assigned a value of 0 or 1 to train the model, where 0 indicates that the verification warning coefficient is less than the verification warning coefficient threshold, and 1 indicates that the verification warning coefficient is greater than the verification warning coefficient threshold.

10. The two-way trusted identity authentication system based on offline files is used to implement the two-way trusted identity authentication method based on offline files according to any one of claims 1 to 9, characterized in that: It includes data acquisition module, data analysis module, safety assessment module, trust assessment module and neural network early warning module, and the signal connections between the modules; A data collection module is used to evaluate the randomness of the key based on the calculated entropy value of the key, and analyze the key entropy at different time points to obtain randomness data; The data analysis module is used to evaluate the effectiveness of encrypted transmission and obtain strength data based on the bit error rate that occurs during the transmission process; The security assessment module is used to analyze randomness data and strength data to quantify the security of two-way trusted identity authentication in multi-point transmission scenarios within a time range; A trust evaluation module is used to generate similar data based on comparing the historical data of the receiving node and the characteristics of the current transmission file, analyze the response time of the transmission process, generate performance data, and evaluate the trust of the transmission process; The neural network early warning module is used to use the quantitative results of security and trust in the transmission process as the input of the neural network, train the model, and predict potential abnormal situations.

Images