A network security testing method and system based on big data

By obtaining the status emergency index and attack margin of network access data, and combining the network access relationship diagram to analyze the nearest neighbor differences characteristics of the disguiser node, the problems of high false alarm rate and single test mode in network security test in the existing technology are solved, and the problem of high false alarm rate and single test mode in network security test is realized. More accurate network security assessment and detection.

CN118827242BActive Publication Date: 2024-11-22BEIJING TRUSFORT TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411304065.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-19
Publication Date
2024-11-22
Estimated Expiration
2044-09-19

AI Technical Summary

Technical Problem

The existing network security testing methods have high false positive rates and single test modes when identifying potential stealing camouflage and attacks, which lead to sparse characteristics and cannot effectively deal with the challenges of stealing camouflage and attacks.

Method used

By obtaining the state emergency index and attack margin of network access data, potential stealing camouflage features are extracted, and the nearest neighbor differences characteristics of the disguiser nodes are analyzed in combination with the network access relationship diagram, and a security testing strategy is formulated to improve detection accuracy.

Benefits of technology

It realizes a more comprehensive and accurate network security assessment, which can accurately locate potential security risks, simulate real attack scenarios, reduce false alarm rates, and improve the accuracy of security test results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118827242B_ABST
    Figure CN118827242B_ABST
Patent Text Reader

Abstract

The present application provides a network security testing method and system based on big data, which obtains a network access array for a target network; assigns a state to each network access data in the network access array according to the security check margin of the target network, obtains a state emergency index corresponding to each network access data, and determines the state theft coefficient when accessing the target network through all the state emergency indexes; obtains a network access relationship graph, extracts all pretender nodes in the network access relationship graph, determines the neighbor difference characteristics of each pretender node, and determines the attack margin of all pretender nodes to the target network based on all the neighbor difference characteristics; performs a security test on the target network based on the state theft coefficient and the attack margin, and obtains the security test result of the target network. The above scheme can be used to extract potential theft disguise features in network access data to better cope with the theft disguise and attack challenges faced by network security testing.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of security testing technology, and more specifically, to a network security testing method and system based on big data. Background Art

[0002] Big data-based network security testing is an emerging network security assessment method that identifies potential threats, vulnerabilities, and abnormal behaviors by collecting and analyzing data from various network activities and devices. This method utilizes big data analysis technologies, including machine learning, deep learning, data mining, etc. By processing massive amounts of data, it can identify complex attack patterns and unknown threats in a wider network environment, and improve the intelligence and automation level of network security protection.

[0003] Network security testing involves a large amount of access data from different devices, applications, and network layers. These access data are not only extremely large in magnitude, but also diverse in structure, including log data, traffic data, system call records, etc. In the prior art, although the application of machine learning and artificial intelligence technology in network security can improve the accuracy of threat detection, it may also produce a high false alarm rate. False alarms not only waste computing resources, but may also cause actual unauthorized theft and attacks to be ignored. When conducting security testing on the target network, there is a problem of a single test mode, which leads to sparse features during the security testing process and the inability to comprehensively conduct security testing on the target network. Therefore, how to extract potential theft disguise features in network access data to better cope with the challenges of theft disguise and attack faced by network security testing is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a network security testing method and system based on big data, which can extract potential theft and disguise features in network access data to better cope with the theft, disguise and attack challenges faced by network security testing.

[0005] In a first aspect, the present application provides a network security testing method based on big data, comprising the following steps:

[0006] Start a security test on the target network and obtain the network access array of the target network;

[0007] Determine the security check margin of the target network, assign a state to each network access data in the network access array according to the security check margin, obtain a state emergency index corresponding to each network access data, and determine a state theft coefficient when accessing the target network through all the state emergency indexes;

[0008] Obtain a network access relationship graph of the target network, extract all pretender nodes from the network access relationship graph, and then determine the neighbor difference characteristics of each pretender node, and determine the attack margin of all pretender nodes on the target network based on all the neighbor difference characteristics;

[0009] A security test is performed on the target network according to the state theft coefficient and the attack margin to obtain a security test result of the target network.

[0010] In some embodiments, determining the security check margin of the target network specifically includes:

[0011] Obtaining the node access margin of the target network;

[0012] Determining a security verification load of the target network according to the node access margin and the total number of current access nodes of the target network;

[0013] The security check margin of the target network is determined by the security check load.

[0014] In some embodiments, assigning a state to each network access data in the network access array according to the security check margin to obtain a state emergency index corresponding to each network access data specifically includes:

[0015] Constructing a state allocation function of a target network through the safety check margin;

[0016] For each network access data in the network access array, the state allocation function is used to allocate the state of the network access data to obtain the state emergency index corresponding to the network access data, and then obtain the state emergency index corresponding to each network access data.

[0017] In some embodiments, determining the state stealing coefficient when accessing the target network through all state emergency indexes specifically includes:

[0018] Convert all state urgency indices into a state urgency matrix of the target network;

[0019] Extracting stealing features from the state emergency matrix to obtain a plurality of state stealing features;

[0020] The state theft coefficient when accessing the target network is determined based on all state theft characteristics.

[0021] In some embodiments, extracting all pretender nodes in the network access relationship graph specifically includes:

[0022] Obtaining access characteristics of each access node in the network access relationship graph;

[0023] For each access node, anomaly identification is performed according to the access characteristics of the access node to obtain the access disguise degree of the access node, and then the access disguise degree of each access node is obtained;

[0024] The access nodes whose access masquerade degree exceeds the set threshold are regarded as masquerade nodes, and then all masquerade nodes are obtained.

[0025] In some embodiments, determining the neighbor difference feature of each pretender node specifically includes:

[0026] For each pretender node, obtain all neighboring nodes of the pretender node in the network access relationship graph;

[0027] Determine the neighbor difference value between the pretender node and each neighbor node respectively;

[0028] The neighbor difference feature of the pretender node is determined by all the neighbor difference values, and then the neighbor difference feature of each pretender node is obtained.

[0029] In some embodiments, performing security testing on a target network according to the state theft coefficient and the attack margin specifically includes:

[0030] Formulate a security test strategy for the target network using the state theft coefficient and the attack margin;

[0031] A security test is performed on the target network based on the security test strategy.

[0032] In a second aspect, the present application provides a network security testing system based on big data, including a security testing unit, wherein the security testing unit includes:

[0033] An acquisition module is used to initiate a security test on a target network and obtain a network access array for the target network;

[0034] A processing module, used to determine the security check margin of the target network, assign a state to each network access data in the network access array according to the security check margin, obtain a state emergency index corresponding to each network access data, and determine a state theft coefficient when accessing the target network through all the state emergency indexes;

[0035] The processing module is further used to obtain a network access relationship graph of the target network, extract all pretender nodes from the network access relationship graph, and then determine the neighbor difference characteristics of each pretender node, and determine the attack margin of all pretender nodes on the target network based on all the neighbor difference characteristics;

[0036] The execution module is used to perform a security test on the target network according to the state theft coefficient and the attack margin to obtain a security test result of the target network.

[0037] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned big data-based network security testing method.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned big data-based network security testing method when executed.

[0039] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0040] The present application provides a network security testing method and system based on big data, which includes starting a security test on a target network, obtaining a network access array for the target network, determining a security check margin for the target network, assigning a state to each network access data in the network access array according to the security check margin, obtaining a state emergency index corresponding to each network access data, and determining a state theft coefficient when accessing the target network through all state emergency indexes; obtaining a network access relationship graph for the target network, extracting all pretender nodes from the network access relationship graph, and further determining a neighbor difference feature of each pretender node, and determining an attack margin of all pretender nodes to the target network based on all neighbor difference features; performing a security test on the target network according to the state theft coefficient and the attack margin, and obtaining a security test result for the target network.

[0041] It can be seen that in this application, potential theft disguise features in network access data can be extracted; wherein, by associating the state of network access data with the security check margin, the security status of the network can be more comprehensively evaluated, and the state emergency index corresponding to each network access data can be determined, which helps to accurately locate the potential security risks in the target network. The state theft coefficient can extract potential theft disguise features by comprehensively considering all state emergency indexes; then, through the network access relationship graph, those pretender nodes disguised as normal access behaviors can be identified, and by analyzing the neighbor difference characteristics of the pretender nodes and calculating the attack margin on the target network, the attack potential of each pretender node in the network can be evaluated in real time, and a closer attack scenario to the real one can be simulated in network security testing; finally, the target network is security tested in combination with the state theft coefficient and the attack margin to obtain more accurate security test results. In summary, the technical solution adopted in this application can extract potential theft disguise features in network access data to better cope with the theft disguise and attack challenges faced by network security testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0043] Figure 1 is an exemplary flow chart of a network security testing method based on big data according to some embodiments of the present application;

[0044] Figure 2 is an exemplary flow chart of determining a safety check margin according to some embodiments of the present application;

[0045] Figure 3 is an exemplary flow chart of determining neighbor difference features according to some embodiments of the present application;

[0046] Figure 4 is a schematic diagram of exemplary hardware and / or software of a safety test unit according to some embodiments of the present application;

[0047] Figure 5 It is a structural diagram of a computer device for implementing a network security testing method based on big data as shown in some embodiments of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] The embodiment of the present application provides a network security testing method and system based on big data, the core of which is to start a security test on the target network, obtain a network access array for the target network; determine the security check margin of the target network, and assign a state to each network access data in the network access array according to the security check margin, obtain the state emergency index corresponding to each network access data, and determine the state theft coefficient when accessing the target network through all the state emergency indexes; obtain the network access relationship graph of the target network, extract all the pretender nodes in the network access relationship graph, and then determine the neighbor difference characteristics of each pretender node, and determine the attack margin of all pretender nodes to the target network based on all the neighbor difference characteristics; perform a security test on the target network according to the state theft coefficient and the attack margin, and obtain the security test result of the target network. The above scheme can be used to extract potential theft disguise features in network access data to better cope with the theft disguise and attack challenges faced by network security testing.

[0050] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a network security testing method based on big data according to some embodiments of the present application. The network security testing method 100 based on big data mainly includes the following steps:

[0051] In step 101, a security test on a target network is initiated to obtain a network access array for the target network.

[0052] In the specific implementation, first, start the security test of the target network; then, you can obtain multiple network access data of the target network through the API gateway, the network access data includes the visitor's IP address, port number, access type, data packet size, access path and access time, so that all network access data can be arranged according to the corresponding nodes to obtain a matrix, which can be used as the network access array of the target network, that is, the network access array contains multiple network access data of the target network.

[0053] In step 102, the security check margin of the target network is determined, and the state of each network access data in the network access array is assigned according to the security check margin to obtain the state emergency index corresponding to each network access data, and the state theft coefficient when accessing the target network is determined by all the state emergency indexes.

[0054] Preferably, in some embodiments, reference Figure 2 As shown, this figure is an exemplary flow chart of determining the security check margin in some embodiments of the present application. In this embodiment, determining the security check margin of the target network can be implemented by the following steps:

[0055] In step 1021, a node access margin of a target network is obtained;

[0056] In step 1022, the security verification load of the target network is determined according to the node access margin and the total number of current access nodes of the target network;

[0057] In step 1023, the security verification margin of the target network is determined by using the security verification load.

[0058] It should be noted that, in the present application, the node access margin refers to the additional node access amount that the target network can withstand without significantly affecting network security; the security verification load refers to the total amount of security inspection and verification tasks that the target network needs to undertake based on the node access margin. The security verification load reflects the security inspection pressure of the target network under the current access load; the security verification margin indicates the security verification capacity that the target network can currently carry. If the security verification margin is a positive value, it means that the target network has sufficient safety margin under the current load. If it is a negative value, it means that the target network may face an excessively high security inspection burden and needs to be optimized.

[0059] In the specific implementation, first, the node access margin of the target network is obtained. The node capacity and the current node configuration of the target network can be obtained through the network management system, and the current node configuration amount is subtracted from the node capacity of the target network, and the result can be used as the node access margin of the target network; then, the total number of access nodes currently in the target network is obtained, and the access nodes include all user devices, servers, sensors, etc., and the node access margin is normalized, so as to calculate the sum of the node loads corresponding to each access node in the target network and then divide it by the normalized node access margin, and the result can be used as the security verification load of the target network; finally, the security verification margin of the target network is determined by the security verification load, that is, the node access margin is subtracted from the security verification load to obtain the security verification margin of the target network.

[0060] Optionally, in some embodiments, the state of each network access data in the network access array is assigned according to the security check margin, and the state emergency index corresponding to each network access data is obtained in the following manner, namely:

[0061] Constructing a state allocation function of a target network through the safety check margin;

[0062] For each network access data in the network access array, the state allocation function is used to allocate the state of the network access data to obtain the state emergency index corresponding to the network access data, and then obtain the state emergency index corresponding to each network access data.

[0063] In the specific implementation, first, the state allocation function of the target network can be constructed through the security check margin, and the state allocation function can be expressed in the following way: state allocation function = network access data * warning number / security check margin, where the warning number is a number between 0 and 1 set according to historical experiments; then, for each network access data in the network access array, the state allocation function is used to allocate the state of the network access data, that is, the network access data is input into the state allocation function for calculation, and the value of the state allocation function is used as the corresponding state emergency index of the network access data. The state emergency index corresponding to each network access data can be obtained in the above manner. The state emergency index is used to indicate the state urgency of the network access data. The larger the state emergency index, the more urgent the state of the network access data, and the greater the probability that the network access data is stolen.

[0064] Optionally, in some embodiments, the state stealing coefficient when accessing the target network can be determined by all state emergency indexes in the following manner, namely:

[0065] Convert all state urgency indices into a state urgency matrix of the target network;

[0066] Extracting stealing features from the state emergency matrix to obtain a plurality of state stealing features;

[0067] The state theft coefficient when accessing the target network is determined based on all state theft characteristics.

[0068] It should be noted that in the present application, the state emergency matrix is ​​a data structure that organizes all state emergency indices into a matrix form, in which each element represents the emergency index of the corresponding network access data; the state theft feature is a feature used to represent the theft behavior in the network access data; the state theft coefficient represents the state theft probability faced by the target network when all network access data access the target network.

[0069] In the specific implementation, first, all the state urgency indexes are arranged according to the dimension of the network access data to form a matrix, which can be used as the state urgency matrix of the target network; then, the state urgency matrix is ​​subjected to stealing feature extraction, that is, the state urgency matrix is ​​decomposed using the principal component analysis method to obtain multiple decomposed feature vectors, which can be used as state stealing features, that is, multiple state stealing features are obtained; finally, each state stealing feature can be standardized to eliminate the scale difference between different state stealing features, so that the standard deviation of all standardized state stealing features can be used as the state stealing coefficient when accessing the target network.

[0070] It should be noted that by associating the status of network access data with the security verification margin, the security status of the network can be evaluated more comprehensively, and the status emergency index corresponding to each network access data can be determined, which helps to accurately locate possible security risks in the target network. In this way, more detailed inspections and optimizations can be carried out on high-risk areas, thereby improving the overall security of the target network. The status theft coefficient can extract potential theft disguise features by comprehensively considering all status emergency indices.

[0071] In step 103, a network access relationship graph of the target network is obtained, all pretender nodes are extracted from the network access relationship graph, and then the neighbor difference characteristics of each pretender node are determined, and the attack margin of all pretender nodes on the target network is determined based on all the neighbor difference characteristics.

[0072] It should be noted that in the present application, the network access relationship diagram is a relationship diagram used to represent the association between various access nodes; in specific implementation, all access nodes in the target network can be obtained, and the network access data corresponding to each access node can be obtained in the network access array of the target network, so as to establish the relationship between the access nodes based on the network access data and draw it into a relationship diagram, that is, to obtain the network access relationship diagram of the target network.

[0073] Optionally, in some embodiments, extracting all pretender nodes in the network access relationship graph may be performed in the following manner, namely:

[0074] Obtaining access characteristics of each access node in the network access relationship graph;

[0075] For each access node, anomaly identification is performed according to the access characteristics of the access node to obtain the access disguise degree of the access node, and then the access disguise degree of each access node is obtained;

[0076] The access nodes whose access masquerade degree exceeds the set threshold are regarded as masquerade nodes, and then all masquerade nodes are obtained.

[0077] In the specific implementation, first, the access characteristics of each access node are extracted from the network access relationship graph. The access characteristics include the access frequency, access time, data traffic, communication mode and request type of the access node; then, for each access node, anomaly identification is performed based on the access characteristics of the access node. Appropriate anomaly detection algorithms (such as isolation forest and local outlier factor) can be used to identify anomalies in the access characteristics, so that the anomaly detection result of the access node can be obtained. The anomaly detection result indicates the degree of difference between the access node and the normal node, so that the anomaly detection result can be used as the access disguise degree of the access node. The access disguise degree is used to indicate the degree of suspicion of disguise of the access node. The access disguise degree of each access node can be obtained in the above manner; finally, a threshold value of the access disguise degree is set. The threshold value can be set according to the normal behavior mode and security requirements of the target network, and is usually a dynamic or empirical value, so that the access node whose access disguise degree exceeds the set threshold is marked as a disguise node. The disguise node shows significant anomalies in the access characteristics, which may be a malicious node trying to disguise a normal access node.

[0078] Preferably, in some embodiments, reference Figure 3 As shown in FIG. 1 , this figure is an exemplary flow chart of determining neighbor difference features in some embodiments of the present application. In this embodiment, determining the neighbor difference features of each pretender node can be implemented by the following steps:

[0079] In step 1031, for each pretender node, all neighboring nodes of the pretender node are obtained in the network access relationship graph;

[0080] In step 1032, the neighbor difference value between the pretender node and each neighbor node is determined respectively;

[0081] In step 1033, the neighbor difference feature of the pretender node is determined by all the neighbor difference values, and then the neighbor difference feature of each pretender node is obtained.

[0082] In the specific implementation, first, for each pretender node, in the network access relationship graph, all neighboring nodes of the pretender node are found, and the neighboring node refers to the access node directly connected to the pretender node; then, the neighbor difference value between the pretender node and each neighboring node is calculated respectively, and the neighbor difference value can be represented by the first normal form distance interpolation between the access camouflage degree of the pretender node and the access camouflage degree of the neighboring node, and the neighbor difference value is used to represent the degree of difference between the pretender node and the neighboring node; finally, the neighbor difference feature of the pretender node is determined by all the neighbor difference values, that is, the average of all the neighbor difference values ​​is used as the neighbor difference feature of the pretender node, and the neighbor difference feature is used to represent the overall degree of difference between the pretender node and all its neighboring nodes. The neighbor difference feature of each pretender node can be obtained by the above method.

[0083] Preferably, in some embodiments, the attack margin of all pretender nodes on the target network is determined based on all neighbor difference characteristics in the following manner, namely:

[0084] The weighted sum of the neighbor difference features of all pretender nodes is performed to obtain the attack potential score of each pretender node;

[0085] Determine the attack probability of each pretender node on the target network based on the corresponding attack potential score;

[0086] The attack margin of all pretender nodes on the target network is determined by all attack probabilities.

[0087] It should be noted that, in the present application, the attack potential score indicates the possible degree of attack of the pretender node on the target network. The attack potential score indicates that the greater the possibility of the pretender node attacking the target network; the attack margin indicates the risk level of the target network to withstand the attack in the current state.

[0088] In the specific implementation, first, the neighbor difference features of all pretender nodes are weighted and summed, and the weight can be set according to the importance of each neighbor difference feature and the relevance to the attack behavior. The proportion of the weighted value of the neighbor difference feature of the pretender node in the weighted values ​​of all neighbor difference features can be used as the attack potential score of the pretender node. The attack potential score of each pretender node can be obtained in the above manner; then, for each pretender node, the attack potential score can be converted into an attack probability using a probability distribution model (such as Gaussian distribution, exponential distribution, etc.), and the attack probability of each pretender node on the target network can be obtained; finally, the attack margin of all pretender nodes on the target network is determined by all attack probabilities, that is, all attack probabilities are accumulated, and the result is used as the attack margin on the target network.

[0089] It should be noted that through the network access relationship graph, those pretender nodes that disguise themselves as normal access behaviors can be identified. Pretender nodes may try to hide their true intentions in the network and perform theft or attack behaviors. By analyzing the neighbor difference characteristics of the pretender nodes and calculating the attack margin on the target network, the attack potential of each pretender node in the network can be evaluated in real time, and more realistic attack scenarios can be simulated in network security tests.

[0090] In step 104, a security test is performed on the target network according to the state theft coefficient and the attack margin to obtain a security test result of the target network.

[0091] Optionally, in some embodiments, the security test of the target network according to the state theft coefficient and the attack margin may be performed in the following manner, namely:

[0092] Formulate a security test strategy for the target network using the state theft coefficient and the attack margin;

[0093] A security test is performed on the target network based on the security test strategy.

[0094] In the specific implementation, first, the state theft coefficient and the attack margin are combined to determine the priority of the security test, giving priority to areas with high state theft coefficients and high attack margins, and determining the network areas or nodes that need to be tested in focus, which may have higher risks and may have potential attack threats, so as to select appropriate security testing methods according to the determined test goals and priorities, such as penetration testing, vulnerability scanning, simulated attacks, etc., to obtain a security testing strategy for the target network; then, configure and prepare tools and scripts for testing, so as to perform penetration testing on high-risk areas of the target network, simulate the behavior of attackers, and test the defense capabilities of the network; finally, the security test results of the target network can be obtained in the above manner, and the security test results contain weaknesses and potential threats in the target network, so that corresponding protection measures can be formulated and implemented according to the security test results, the vulnerabilities found in the test can be repaired, and the defense capabilities of the target network can be enhanced.

[0095] It can be seen that in this application, potential theft disguise features in network access data can be extracted; wherein, by associating the state of network access data with the security check margin, the security status of the network can be more comprehensively evaluated, and the state emergency index corresponding to each network access data can be determined, which helps to accurately locate the potential security risks in the target network. The state theft coefficient can extract potential theft disguise features by comprehensively considering all state emergency indexes; then, through the network access relationship graph, those pretender nodes disguised as normal access behaviors can be identified, and by analyzing the neighbor difference characteristics of the pretender nodes and calculating the attack margin on the target network, the attack potential of each pretender node in the network can be evaluated in real time, and a closer attack scenario to the real one can be simulated in network security testing; finally, the target network is security tested in combination with the state theft coefficient and the attack margin to obtain more accurate security test results. In summary, the technical solution adopted in this application can extract potential theft disguise features in network access data to better cope with the theft disguise and attack challenges faced by network security testing.

[0096] In addition, in another aspect of the present application, in some embodiments, the present application provides a network security testing system based on big data, the network security testing system based on big data includes a security testing unit, reference Figure 4 , which is a schematic diagram of exemplary hardware and / or software of a security test unit according to some embodiments of the present application, the security test unit 400 includes: an acquisition module 401, a processing module 402 and an execution module 403, which are described as follows:

[0097] Acquisition module 401, in this application, acquisition module 401 is mainly used to start security testing of the target network and obtain a network access array for the target network;

[0098] Processing module 402, in the present application, is used to determine the security check margin of the target network, assign a state to each network access data in the network access array according to the security check margin, obtain a state emergency index corresponding to each network access data, and determine a state theft coefficient when accessing the target network through all state emergency indexes;

[0099] It should be noted that the processing module 402 in the present application is also used to obtain a network access relationship graph of the target network, extract all pretender nodes in the network access relationship graph, and then determine the neighbor difference characteristics of each pretender node, and determine the attack margin of all pretender nodes on the target network based on all neighbor difference characteristics;

[0100] Execution module 403, in the present application, execution module 403 is mainly used to perform security test on the target network according to the state theft coefficient and the attack margin to obtain the security test result of the target network.

[0101] The above describes in detail the examples of the network security testing method and system based on big data provided by the embodiments of the present application. It can be understood that the corresponding device includes a hardware structure and / or software module corresponding to each function in order to realize the above functions. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware 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 the present application.

[0102] In some embodiments, the present application also provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned big data-based network security testing method.

[0103] In some embodiments, reference Figure 5 , the dotted line in the figure indicates that the unit or the module is optional, and the figure is a schematic diagram of the structure of a computer device according to a network security testing method based on big data provided in an embodiment of the present application. The network security testing method based on big data described in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device 500 can be a terminal device, a server or a chip.

[0104] The processor 501 may be a general-purpose processor or a special-purpose processor. For example, the processor 501 may be a central processing unit (CPU), which may be used to control the computer device 500, execute software programs, and process data of the software programs. The computer device 500 may also include a communication unit 505 to implement signal input (reception) and output (transmission).

[0105] For example, the computer device 500 may be a chip, the communication unit 505 may be an input and / or output circuit of the chip, or the communication unit 505 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other devices.

[0106] For another example, the computer device 500 may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0107] The computer device 500 may include one or more memories 502, on which a program 504 is stored. The program 504 can be executed by the processor 501 to generate instructions 503, so that the processor 501 performs the method described in the above method embodiment according to the instructions 503. Optionally, data (such as a target audit model) may also be stored in the memory 502. Optionally, the processor 501 may also read the data stored in the memory 502, and the data may be stored at the same storage address as the program 504, or the data may be stored at a different storage address from the program 504.

[0108] The processor 501 and the memory 502 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0109] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 501. The processor 501 can be a central processing unit, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, such as discrete gates, transistor logic devices or discrete hardware components.

[0110] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0111] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned big data-based network security testing method when executed.

[0112] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0113] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A network security testing method based on big data, characterized in that: The steps include: Start a security test on the target network and obtain the network access array of the target network; Determine the security check margin of the target network, assign a state to each network access data in the network access array according to the security check margin, obtain a state emergency index corresponding to each network access data, and determine a state theft coefficient when accessing the target network through all the state emergency indexes; Among them, determining the security verification margin of the target network specifically includes: Obtaining the node access margin of the target network; Determining a security verification load of the target network according to the node access margin and the total number of current access nodes of the target network; Determining the security verification margin of the target network through the security verification load; The state of each network access data in the network access array is assigned according to the security check margin to obtain the state emergency index corresponding to each network access data, which specifically includes: Constructing a state allocation function of a target network through the safety check margin; For each network access data in the network access array, using the state allocation function to allocate the state of the network access data, obtain the state emergency index corresponding to the network access data, and then obtain the state emergency index corresponding to each network access data; Among them, the state theft coefficient when accessing the target network is determined by all state emergency indexes, specifically including: Convert all state urgency indices into a state urgency matrix of the target network; Extracting stealing features from the state emergency matrix to obtain a plurality of state stealing features; Determine the state theft coefficient when accessing the target network based on all state theft characteristics; Obtain a network access relationship graph of the target network, extract all pretender nodes from the network access relationship graph, and then determine the neighbor difference characteristics of each pretender node, and determine the attack margin of all pretender nodes on the target network based on all the neighbor difference characteristics; A security test is performed on the target network according to the state theft coefficient and the attack margin to obtain a security test result of the target network.

2. The method according to claim 1, characterized in that Extracting all pretender nodes in the network access relationship graph specifically includes: Obtaining access characteristics of each access node in the network access relationship graph; For each access node, anomaly identification is performed according to the access characteristics of the access node to obtain the access disguise degree of the access node, and then the access disguise degree of each access node is obtained; The access nodes whose access masquerade degree exceeds the set threshold are regarded as masquerade nodes, and then all masquerade nodes are obtained.

3. The method according to claim 1, characterized in that Determine the neighbor difference characteristics of each pretender node specifically include: For each pretender node, obtain all neighboring nodes of the pretender node in the network access relationship graph; Determine the neighbor difference value between the pretender node and each neighbor node respectively; The neighbor difference feature of the pretender node is determined by all the neighbor difference values, and then the neighbor difference feature of each pretender node is obtained.

4. The method according to claim 1, characterized in that The security test of the target network according to the state theft coefficient and the attack margin specifically includes: Formulate a security test strategy for the target network using the state theft coefficient and the attack margin; A security test is performed on the target network based on the security test strategy.

5. A network security testing system based on big data, the network security testing system based on big data includes a security testing unit, characterized in that: The safety testing unit comprises: An acquisition module is used to initiate a security test on a target network and obtain a network access array for the target network; A processing module, used to determine the security check margin of the target network, assign a state to each network access data in the network access array according to the security check margin, obtain a state emergency index corresponding to each network access data, and determine a state theft coefficient when accessing the target network through all the state emergency indexes; Among them, determining the security verification margin of the target network specifically includes: Obtaining the node access margin of the target network; Determining a security verification load of the target network according to the node access margin and the total number of current access nodes of the target network; Determining the security verification margin of the target network through the security verification load; The state of each network access data in the network access array is assigned according to the security check margin to obtain the state emergency index corresponding to each network access data, which specifically includes: Constructing a state allocation function of a target network through the safety check margin; For each network access data in the network access array, using the state allocation function to allocate the state of the network access data, obtain the state emergency index corresponding to the network access data, and then obtain the state emergency index corresponding to each network access data; Among them, the state theft coefficient when accessing the target network is determined by all state emergency indexes, specifically including: Convert all state urgency indices into a state urgency matrix of the target network; Extracting stealing features from the state emergency matrix to obtain a plurality of state stealing features; Determine the state theft coefficient when accessing the target network based on all state theft characteristics; The processing module is further used to obtain a network access relationship graph of the target network, extract all pretender nodes from the network access relationship graph, and then determine the neighbor difference characteristics of each pretender node, and determine the attack margin of all pretender nodes on the target network based on all the neighbor difference characteristics; The execution module is used to perform a security test on the target network according to the state theft coefficient and the attack margin to obtain a security test result of the target network.

6. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the big data-based network security testing method described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions or codes, and when the instructions or codes are executed on a computer, the computer implements the network security testing method based on big data as described in any one of claims 1 to 4.

Citation Information

Patent Citations

  • Power flow scheduling optimization method for multi-terminal flexible DC power distribution network

    CN113890039A

  • Network intrusion prevention method and system based on high-order camouflage deception technology

    CN118214583A

  • Network security protection method and apparatus

    WO2022127482A1