Efficiency evaluation method, device and equipment for endogenous security e-government affair system

Abstract

The invention discloses an endogenous security e-government system efficiency evaluation method, device and equipment, and the method comprises the steps: collecting target data from an e-government system, and carrying out the preprocessing of the collected data; carrying out normalization processing on the preprocessed data according to categories; inputting the normalized data into an input layer of a neural network model; performing nonlinear transformation and feature extraction on the input data by the neural network model to obtain an evaluation value; and judging the security of the e-government affair system according to the evaluation value. According to the method, nonlinear transformation and feature extraction can be carried out by fully utilizing the multi-dimensional data in the e-government affair system, so that a complex nonlinear relationship in the system is accurately captured and evaluated, the accuracy and efficiency of risk evaluation are improved, a new risk mode can be automatically adapted and learned, and dynamic monitoring and early warning of risks are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of system performance evaluation, and in particular to a method, device and equipment for evaluating the performance of an intrinsically secure e-government system. Background Art

[0002] In the current field of e-government system security assessment, there are many assessment methods, but the existing technical solutions still have significant deficiencies in accuracy and practicality. Specifically, the existing e-government information security assessment methods are mainly divided into qualitative assessment, quantitative assessment, and qualitative and quantitative combined assessment methods. However, these methods are often difficult to accurately reflect the real security status of the system when faced with the complexity and nonlinear characteristics of the e-government system.

[0003] E-government systems are extremely vulnerable to attacks by criminals due to the particularity and sensitivity of the data they transmit. If an e-government system is attacked, the damage it causes is immeasurable in terms of scope and degree of damage, and may even threaten national security. Therefore, it is particularly important to accurately assess the security of e-government systems.

[0004] Existing evaluation methods, such as the patent document with invention publication number 201910562544.X, which discloses a security evaluation method for an e-government system, can reflect the security of the system to a certain extent, but are limited by their linear evaluation models and fixed evaluation indicators, making it difficult to accurately capture and evaluate the complex nonlinear relationships in the e-government system. For example, existing methods ignore the comprehensive impact of multi-dimensional data such as operating system information, instruction setting information, virus library update cycle, R&D personnel loss information, website domain name filing information, real-name authentication information of registered users, data backup information, system update cycle, memory usage, e-government system click volume, user login information, IP access information, and illegal information emergency response mechanism on system security, thereby affecting the accuracy and reliability of the evaluation results. Summary of the invention

[0005] The main purpose of this application is to provide a method, device and equipment for evaluating the effectiveness of an intrinsically secure e-government system, aiming to solve the problem in the prior art that it is difficult to accurately capture and evaluate complex nonlinear relationships in e-government systems.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for evaluating the effectiveness of an intrinsically secure e-government system, comprising the following steps:

[0008] S1, collect target data from the e-government system and pre-process the collected data;

[0009] S2, normalizing the preprocessed data by category;

[0010] S3, input the normalized data into the input layer of the neural network model;

[0011] S4, the neural network model performs nonlinear transformation and feature extraction on the input data to obtain an evaluation value;

[0012] S5. Determine the security of the e-government system based on the evaluation value. If the evaluation result shows that the system is secure, end the evaluation and output the result. If the evaluation result shows that the system is not secure, adjust and optimize the target data in the system based on specific security vulnerabilities and risk points, and repeat steps S1 to S5 to verify the adjustment effect.

[0013] Optionally, the target data collected in step S1 includes system log data, system performance data and user behavior data.

[0014] Optionally, the following formula is used for normalization processing in step S2:

[0015]

[0016] Among them, x is the original data, mean(x) is the data mean, std(x) is the data standard deviation, and y is the normalized data.

[0017] Optionally, the neural network model in step S3 is a three-layer neural network model of 37-10-1, which is specifically expressed as:

[0018] Input layer: There are 37 nodes, each of which corresponds to an e-government system risk assessment indicator;

[0019] Hidden layer: has 10 nodes, and its output is h i The value after being processed by the activation function σ is

[0020]

[0021] Among them, V ij is the weight connecting the input layer node i and the hidden layer node j, a j is the bias of hidden layer node j;

[0022] Output layer: a single node, outputs the comprehensive evaluation value y, that is

[0023]

[0024] Among them, W jz is the weight connecting the hidden layer node j and the output layer node z, and b is the bias of the output layer.

[0025] Optionally, the specific operation steps of step S4 are as follows:

[0026] S4.1, initialize the weights and biases of the neural network model;

[0027] S4.2. Use the back propagation algorithm to train the neural network model, and update the weights and biases through continuous iterations to minimize the error between the predicted value and the actual value;

[0028] S4.3. During the training process, the cross-validation method is used to evaluate the generalization ability of the model to prevent overfitting.

[0029] S4.4. After training is completed, the model is tested using the test data set to verify the accuracy and reliability of the model;

[0030] S4.5. Input the data into the trained model for nonlinear transformation and feature extraction to obtain the evaluation value.

[0031] Optionally, in step S5, if the system security assessment fails, the process further includes:

[0032] S5.1. Identify specific risk points and vulnerabilities that cause system insecurity;

[0033] S5.2. Develop corresponding security strategies and improvement measures based on the identified risk points and vulnerabilities;

[0034] S5.3. Carry out corresponding security reinforcement and optimization operations on the e-government system;

[0035] S5.4. After implementing security reinforcement and optimization operations, restart step S1 to collect target data and conduct a new round of evaluation to verify the effectiveness of the improvement measures.

[0036] In a second aspect, the present application provides an intrinsically secure e-government system performance evaluation device, the intrinsically secure e-government system performance evaluation device comprising:

[0037] The data processing module is used to collect target data from the e-government system, pre-process the collected data, and normalize the pre-processed data by category;

[0038] A neural network model module, which includes an input layer, a hidden layer, and an output layer, and is used to receive normalized data and perform nonlinear transformation and feature extraction to obtain an evaluation value;

[0039] A security judgment module, used to judge the security of the e-government system according to the evaluation value;

[0040] The optimization and verification module is used to achieve continuous optimization and verification of the security of e-government systems.

[0041] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above-mentioned methods for evaluating the effectiveness of an intrinsically secure e-government system.

[0042] Through the above technical scheme, the beneficial effects of the present invention are as follows: by adopting the 37-10-1 three-layer neural network model, the present application can make full use of the multi-dimensional data in the e-government system for nonlinear transformation and feature extraction, so as to accurately capture and evaluate the complex nonlinear relationships in the system, which not only improves the accuracy and efficiency of risk assessment, but also can automatically adapt to and learn new risk models to achieve dynamic monitoring and early warning of risks; through a closed-loop security assessment and improvement process, it continuously discovers and solves security issues in the e-government system and improves the overall security of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and the embodiments in the drawings do not constitute any limitation to the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A flowchart of a method for evaluating the effectiveness of an intrinsically secure e-government system provided in one embodiment of the present application;

[0045] Figure 2 A schematic diagram of the structure of an intrinsically secure e-government system performance evaluation device provided in one embodiment of the present application;

[0046] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application.

[0047] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0048] 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. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0049] The above and other technical contents, features and effects of the present invention are described in detail below with reference to the attached Figure 1-3 The detailed description of the embodiments will clearly show that the structural contents mentioned in the following embodiments are all based on the drawings in the specification.

[0050] Exemplary embodiments of the present invention will be described below with reference to the accompanying drawings.

[0051] The main solutions of the embodiments of this application are:

[0052] like Figure 1 As shown in FIG. 1 , the method for evaluating the effectiveness of an intrinsically secure e-government system includes the following steps:

[0053] S1, collect target data from the e-government system and pre-process the collected data;

[0054] S2, normalizing the preprocessed data by category;

[0055] S3, input the normalized data into the input layer of the neural network model;

[0056] S4, the neural network model performs nonlinear transformation and feature extraction on the input data to obtain an evaluation value;

[0057] S5. Determine the security of the e-government system based on the evaluation value. If the evaluation result shows that the system is secure, end the evaluation and output the result. If the evaluation result shows that the system is not secure, adjust and optimize the target data in the system based on specific security vulnerabilities and risk points, and repeat steps S1 to S5 to verify the adjustment effect.

[0058] In the above, the target data collected in step S1 include system log data, system performance data and user behavior data. Among them, the system log data is key data collected in the log file, such as operating system information, instruction setting information, virus library update cycle, R&D personnel loss information, website domain name filing information, real-name authentication information of registered users, data backup information, system update cycle, etc. System performance data includes memory occupancy rate, CPU usage rate, disk I / O, etc. User behavior data includes e-government system click volume, user login information, IP access information, etc.

[0059] The collected data is cleaned to ensure data quality, remove outliers and irrelevant data, and improve the accuracy of the assessment. During the data cleaning process, statistical analysis methods can be used to identify and remove outliers, and data mining techniques can be used to identify and filter out data that is irrelevant to the assessment target.

[0060] After preprocessing the collected data, the following formula is used for normalization in step S2:

[0061]

[0062] Among them, x is the original data, mean(x) is the data mean, std(x) is the data standard deviation, and y is the normalized data.

[0063] It should be noted that the role of normalization is to eliminate the dimensional differences between data, so that different indicators are comparable. This is crucial for the subsequent use of machine learning algorithms for data analysis. Through normalization, it can ensure that the algorithm is more accurate and efficient when processing data. After completing the normalization process, step S2 also includes further analysis and organization of the data to extract information useful for the performance evaluation of the e-government system.

[0064] Next, step S3 inputs the normalized data into the input layer of the neural network model. The neural network model used in this embodiment is a 37-10-1 three-layer neural network model, which is specifically expressed as:

[0065] Input layer: There are 37 nodes, each of which corresponds to an e-government system risk assessment indicator;

[0066] Hidden layer: has 10 nodes, and its output is h i The value after being processed by the activation function σ is

[0067]

[0068] Among them, V ij is the weight connecting the input layer node i and the hidden layer node j, a j is the bias of hidden layer node j;

[0069] Output layer: a single node, outputs the comprehensive evaluation value y, that is

[0070]

[0071] Among them, W jz is the weight connecting the hidden layer node j and the output layer node z, and b is the bias of the output layer.

[0072] The three-layer neural network model mentioned above is designed to accurately assess the risks of the e-government system through machine learning methods. The model receives rich system feature data through 37 input neurons, uses 10 hidden layer neurons for efficient nonlinear feature extraction and pattern recognition, and finally outputs an accurate risk score through 1 output neuron. This structure not only improves the accuracy and efficiency of risk assessment, but also can automatically adapt to and learn new risk patterns to achieve dynamic monitoring and early warning of risks. In addition, the model has strong generalization ability and can be widely used in different e-government systems, providing strong support for system security management and optimization.

[0073] Next, in step S4, nonlinear transformation and feature extraction are performed on the input data to obtain an evaluation value. The specific operation steps are as follows:

[0074] S4.1. Initialize the weights V of the neural network model ij and W jz , and bias a j and b;

[0075] S4.2. Use the back propagation algorithm to train the neural network model, and update the weights and biases through continuous iterations to minimize the error between the predicted value and the actual value. The specific steps are as follows:

[0076] For each input sample, compute the weighted sum and activation of the hidden layer:

[0077]

[0078] Compute the weighted sum and activation of the output layer:

[0079]

[0080] Calculation error:

[0081]

[0082] Where t is the target output value, 1 means the system is safe, and 0 means the system is unsafe;

[0083] Compute gradients and update weights and biases:

[0084]

[0085] in, is the learning rate, the value is 0.01;

[0086] S4.3. During the training process, the cross-validation method is used to evaluate the generalization ability of the model to prevent overfitting.

[0087] S4.4. After training is completed, the model is tested using the test data set to verify the accuracy and reliability of the model;

[0088] S4.5. Input the data into the trained model for nonlinear transformation and feature extraction to obtain the evaluation value y.

[0089] In the specific implementation process, K-fold cross validation can be used to divide the data set into K subsets, and each subset is used as a validation set in turn. The remaining K-1 subsets are used as training sets. The error of each fold is calculated, and the average value is taken as the generalization error of the model. The role of this K-fold cross validation method is to make full use of the limited data set and evaluate the stability and generalization ability of the model through multiple training and validation. Each validation set is a different subset, so the performance of the model on different data can be fully examined to avoid deviations caused by improper data division.

[0090] In step S5, the security of the e-government system is determined based on the evaluation value, and a security threshold θ is set to determine whether the system is secure:

[0091] If y ≥ θ, the system is safe; if y < θ, the system is unsafe;

[0092] If the system security assessment fails, it will further include:

[0093] S5.1. Identify specific risk points and vulnerabilities that cause system insecurity;

[0094] S5.2. Develop corresponding security strategies and improvement measures based on the identified risk points and vulnerabilities;

[0095] S5.3. Carry out corresponding security reinforcement and optimization operations on the e-government system;

[0096] S5.4. After implementing security reinforcement and optimization operations, restart step S1 to collect target data and conduct a new round of evaluation to verify the effectiveness of the improvement measures.

[0097] The security of the e-government system is evaluated through the neural network model. After security issues are found, specific measures are taken to improve them, and then re-evaluated to verify the effectiveness of the improvement measures. This process forms a closed-loop security assessment and improvement process, which helps to continuously improve the security of the system.

[0098] Based on the same inventive concept, the embodiment of the present application also provides an intrinsic security e-government system performance evaluation device for implementing the intrinsic security e-government system performance evaluation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more intrinsic security e-government system performance evaluation device embodiments provided below can refer to the limitations of the intrinsic security e-government system performance evaluation method above, and will not be repeated here.

[0099] In an exemplary embodiment, Figure 2 The invention provides an intrinsically secure electronic government system performance evaluation device, the intrinsically secure electronic government system performance evaluation device comprising:

[0100] The data processing module is used to collect target data from the e-government system, pre-process the collected data, and normalize the pre-processed data by category;

[0101] A neural network model module, which includes an input layer, a hidden layer, and an output layer, and is used to receive normalized data and perform nonlinear transformation and feature extraction to obtain an evaluation value;

[0102] A security judgment module, used to judge the security of the e-government system according to the evaluation value;

[0103] The optimization and verification module is used to achieve continuous optimization and verification of the security of e-government systems.

[0104] As an optional implementation, the target data includes system log data, system performance data and user behavior data. The data processing module is also used to clean the collected data to ensure data quality, remove outliers and irrelevant data, and improve the accuracy of the evaluation. The pre-processed data is normalized by category to make different indicators comparable.

[0105] As an optional implementation, the neural network model adopted by the neural network model module is a 37-10-1 three-layer neural network model, which receives rich system feature data through 37 input neurons, uses 10 hidden layer neurons to perform efficient nonlinear feature extraction and pattern recognition, and finally outputs an accurate risk score through 1 output neuron.

[0106] As an optional implementation, the security judgment module judges the security of the e-government system based on the evaluation value. If the evaluation result shows that the system is safe, the evaluation ends and the result is output; if the evaluation result shows that the system is not safe, the target data in the system is adjusted and optimized according to the specific security vulnerabilities and risk points. After implementing the security reinforcement and optimization operations, the data processing module is restarted to collect the target data and conduct a new round of evaluation to verify the effectiveness of the improvement measures.

[0107] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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 computer programs in the non-volatile storage medium. The database of the computer device is used to store intrinsic security e-government system effectiveness evaluation data. The input / output interface of the computer device is used to exchange information between the processor and external devices. 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, it implements a method for evaluating the effectiveness of an intrinsic security e-government system. Those skilled in the art can understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0108] 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.

[0109] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0110] 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.

[0111] 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.

[0112] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods 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 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), magnetoresistive 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. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0113] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. 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, etc., but is not limited thereto.

[0114] 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 specification.

[0115] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. The method for evaluating the effectiveness of an intrinsically secure e-government system is characterized by: The steps include: S1, collect target data from the e-government system and pre-process the collected data; S2, normalizing the preprocessed data by category; S3, input the normalized data into the input layer of the neural network model; S4, the neural network model performs nonlinear transformation and feature extraction on the input data to obtain an evaluation value; S5. Determine the security of the e-government system based on the evaluation value. If the evaluation result shows that the system is secure, end the evaluation and output the result. If the evaluation result shows that the system is not secure, adjust and optimize the target data in the system based on specific security vulnerabilities and risk points, and repeat steps S1 to S5 to verify the adjustment effect.

2. The method for evaluating the effectiveness of an intrinsically secure e-government system according to claim 1 is characterized in that: The target data collected in step S1 includes system log data, system performance data and user behavior data.

3. The method for evaluating the effectiveness of an intrinsically secure e-government system according to claim 2 is characterized in that: In step S2, the following formula is used for normalization: Among them, x is the original data, mean(x) is the data mean, std(x) is the data standard deviation, and y is the normalized data.

4. The method for evaluating the effectiveness of an intrinsically secure e-government system according to claim 3 is characterized in that: The neural network model in step S3 is a three-layer neural network model of 37-10-1, which is specifically expressed as follows: Input layer: There are 37 nodes, each of which corresponds to an e-government system risk assessment indicator; Hidden layer: has 10 nodes, and its output is h i The value after being processed by the activation function σ is Among them, V ij is the weight connecting the input layer node i and the hidden layer node j, a j is the bias of hidden layer node j; Output layer: a single node, outputs the comprehensive evaluation value y, that is Among them, W jz is the weight connecting the hidden layer node j and the output layer node z, and b is the bias of the output layer.

5. The method for evaluating the effectiveness of an intrinsically secure e-government system according to claim 4 is characterized in that: The specific operation steps of step S4 are as follows: S4.1, initialize the weights and biases of the neural network model; S4.

2. Use the back propagation algorithm to train the neural network model, and update the weights and biases through continuous iterations to minimize the error between the predicted value and the actual value; S4.

3. During the training process, the cross-validation method is used to evaluate the generalization ability of the model to prevent overfitting. S4.

4. After training is completed, the model is tested using the test data set to verify the accuracy and reliability of the model; S4.

5. Input the data into the trained model for nonlinear transformation and feature extraction to obtain the evaluation value.

6. The method for evaluating the effectiveness of an intrinsically secure e-government system according to claim 5 is characterized in that: In the step S5, if the system security assessment fails, the following steps are further performed: S5.

1. Identify specific risk points and vulnerabilities that cause system insecurity; S5.

2. Develop corresponding security strategies and improvement measures based on the identified risk points and vulnerabilities; S5.

3. Carry out corresponding security reinforcement and optimization operations on the e-government system; S5.

4. After implementing security reinforcement and optimization operations, restart step S1 to collect target data and conduct a new round of evaluation to verify the effectiveness of the improvement measures.

7. An intrinsically secure electronic government system performance evaluation device, characterized in that: The endogenous security e-government system performance evaluation device comprises: The data processing module is used to collect target data from the e-government system, pre-process the collected data, and normalize the pre-processed data by category; A neural network model module, which includes an input layer, a hidden layer, and an output layer, and is used to receive normalized data and perform nonlinear transformation and feature extraction to obtain an evaluation value; A security judgment module, used to judge the security of the e-government system according to the evaluation value; The optimization and verification module is used to achieve continuous optimization and verification of the security of e-government systems.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for evaluating the effectiveness of an intrinsically secure e-government system as described in any one of claims 1 to 6.

Images