Method and system for monitoring industrial control network intrusion in real time
By establishing a baseline model and intrusion prediction model in the industrial control network, combining machine learning algorithms to detect potential intrusion behavior in real time, the problem of lack of foresight and timely response in the existing technology is solved, and the security and emergency response of the industrial control network are significantly improved. ability.
Patent Information
- Application Number
- CN202411173220.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-12-06
AI Technical Summary
The existing technology lacks foresight in real-time monitoring of industrial-controlled network intrusions, and cannot predict possible future data changes or security risks in a timely manner, making it difficult to curb its spread in a timely manner when the danger begins to appear, limiting the ability to reduce potential losses and risks.
By extracting communication data from industrial control networks, establishing a baseline model, and integrating it with machine learning algorithms to build an intrusion prediction model, detecting potential intrusion behavior in real time, formulating a monitoring mechanism based on preset thresholds, and dynamically adjusting the response strategy.
It significantly improves the security of the industrial control network, can keenly detect and respond to potential threats, quickly identify abnormal communication data, reduces manual intervention and monitoring costs, and improves emergency response capabilities and security strategy optimization.
Smart Images

Figure CN119094185A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of industrial automation control, and in particular to a method and system for real-time monitoring of industrial control network intrusion. Background Art
[0002] Industrial control networks, as the cornerstone of industrial automation, rely on specific communication protocols and advanced connection equipment to cleverly weave the complex production processes and automated control systems in the factory into a tight information network. This network not only promotes efficient and accurate data flow between various equipment and systems, but also becomes a strong support for monitoring, controlling and managing the production process. In the modern industrial production system, industrial control networks occupy an indispensable core position.
[0003] In order to ensure the stable operation and data security of industrial control networks, real-time monitoring mechanisms are particularly important. By real-time monitoring of industrial control networks and analyzing monitoring data, abnormal fluctuations or potential signs of intrusion in the network can be detected and identified, so that corresponding measures can be taken in a timely manner to minimize potential losses and risks. In existing real-time monitoring of industrial control network intrusions, data analysis is mainly used to determine whether the network is abnormal, but this usually lacks foresight and cannot predict data changes or security risks that may occur in the industrial control network in the future. When faced with potential intrusions, they can often only adopt a post-event reaction strategy, which makes it difficult to promptly and effectively curb the spread of danger when it first appears, thereby limiting the ability to reduce potential losses and risks.
[0004] Therefore, how to provide a method and system for real-time monitoring of industrial control network intrusion is a problem that needs to be solved urgently. Summary of the invention
[0005] The embodiments of the present invention provide a method and system for real-time monitoring of industrial control network intrusion, so as to solve the above-mentioned technical problems existing in the prior art.
[0006] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not a general review, nor is it intended to identify key / important components or to describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.
[0007] According to a first aspect of an embodiment of the present invention, a method for real-time monitoring of industrial control network intrusion is provided.
[0008] In one embodiment, a method for real-time monitoring of industrial control network intrusion includes: Extract characteristic data based on the communication data in the industrial control network, and analyze the characteristic data to establish the industrial control network baseline model; Integrate feature data with machine learning algorithms to build an industrial control network intrusion prediction model; Input the real-time communication data into the industrial control network intrusion prediction model, output the prediction results, and combine the prediction results with the industrial control network baseline model to perform intrusion detection on the industrial control network; Compare the intrusion detection results with the preset thresholds, and formulate corresponding monitoring mechanisms based on the comparison results.
[0009] In one embodiment, extracting characteristic data based on communication data in the industrial control network and analyzing the characteristic data to establish an industrial control network baseline model includes: Use network packet capture tools to obtain communication data in the industrial control network and pre-process the communication data; Extracting characteristic data from the preprocessed communication data using statistical analysis technology, wherein the characteristic data includes network traffic characteristic data, time pattern characteristic data and behavior abnormality characteristic data; Variance analysis and deviation analysis algorithms are used to analyze the extracted feature data and identify communication variables; Use association rule mining algorithm to mine the communication variables and generate communication association rule discovery; Combining communication association rule discovery with hierarchical clustering algorithm, the pre-processed communication data is classified; Explanatory analysis techniques are used to analyze various types of communication data, and an industrial control network baseline model is established based on the analysis results of various types of communication data.
[0010] In one embodiment, combining communication association rule discovery with a hierarchical clustering algorithm to classify the pre-processed communication data includes: Based on the results of communication association rule discovery, the communication data for hierarchical clustering analysis is screened out; The filtered communication data is used as the initial clustering, and the similarity values between the initial clusters are calculated using the communication similarity formula; Select several clusters with the highest similarity values to merge and generate new clusters; Repeat the clustering merging operation until the preset clustering threshold is reached to obtain the clustering result; According to the clustering results, the preprocessed communication data is allocated to each cluster category to obtain the classification of the communication data.
[0011] In one embodiment, the communication similarity formula is:
[0012] Where, L m,n represents the similarity value between the mth cluster and the nth cluster in the communication data; C mrepresents the mth cluster data set in the communication data, C n represents the nth cluster data set in the communication data; J(C m, C n ) indicates C m With C n ; s represents the number of clusters between the mth cluster and the nth cluster in the communication data; ω represents the adjustment parameter; k represents the number of clusters in the communication data; T m represents the similarity coefficient corresponding to the mth cluster in the communication data; T n represents the similarity coefficient corresponding to the nth cluster in the communication data; T k Represents the similarity coefficient between the mth cluster and the nth cluster in the communication data.
[0013] In one embodiment, the integration of feature data with a machine learning algorithm to construct an industrial control network intrusion prediction model includes: According to the extracted feature data, a feature data set is established, and the feature data set is divided into a training set and a test set; Combine feature data with random forest algorithm to build an initial industrial control network intrusion prediction model; The training set is used to train the initial industrial control network intrusion prediction model, and the test set is used to evaluate the initial industrial control network intrusion prediction model after training to obtain the industrial control network intrusion prediction model.
[0014] In one embodiment, the formula of the industrial control network intrusion prediction model is:
[0015] Where N represents the industrial control network intrusion prediction value; M represents the number of decision trees in the random forest; f z (x) represents the prediction result of the zth decision tree for the input feature data x.
[0016] In one embodiment, the step of inputting the real-time communication data into the industrial control network intrusion prediction model, outputting the prediction result, and combining the prediction result with the industrial control network baseline model to perform intrusion detection on the industrial control network includes: Collect real-time communication data within the industrial control network and pre-process the real-time communication data; Extracting real-time feature data from the pre-processed real-time communication data, and inputting the real-time feature data into the industrial control network intrusion prediction model, and outputting the prediction result; Obtain various feature data based on the industrial control network baseline model; Compare the prediction results with various feature data and calculate the data difference.
[0017] In one embodiment, the monitoring mechanism includes an alarm monitoring mechanism and a network monitoring mechanism.
[0018] In one embodiment, comparing the intrusion detection result with a preset threshold and formulating a corresponding monitoring mechanism according to the comparison result includes: The calculated data difference is compared with the preset threshold, and whether the industrial control network is invaded is determined based on the comparison result; If the data difference is greater than or equal to the preset threshold, the industrial control network is invaded, the alarm monitoring mechanism is activated, and the alarm is sent to the industrial control network administrator; If the data difference is less than the preset threshold, there is no intrusion in the industrial control network and the network monitoring mechanism continues.
[0019] According to a second aspect of an embodiment of the present invention, a system for real-time monitoring of intrusions in an industrial control network is provided.
[0020] In one embodiment, the system for real-time monitoring of industrial control network intrusion includes: The industrial control network baseline model establishment module is used to extract characteristic data based on the communication data in the industrial control network, and analyze the characteristic data to establish the industrial control network baseline model; Industrial control network intrusion prediction model building module, which is used to integrate feature data with machine learning algorithms to build an industrial control network intrusion prediction model; The industrial control network intrusion detection module is used to input real-time communication data into the industrial control network intrusion prediction model, output the prediction results, and combine the prediction results with the industrial control network baseline model to perform intrusion detection on the industrial control network; The intrusion detection result processing module is used to compare the intrusion detection result with the preset threshold value and formulate a corresponding monitoring mechanism according to the comparison result.
[0021] According to a third aspect of an embodiment of the present invention, a computer device is provided.
[0022] In some embodiments, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.
[0023] According to a fourth aspect of embodiments of the present invention, a computer-readable storage medium is provided.
[0024] In one embodiment, the computer-readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.
[0025] The technical solution provided by the embodiment of the present invention may have the following beneficial effects: 1. The present invention establishes a baseline model of the industrial control network by deeply mining the communication data in the industrial control network, thereby accurately describing the behavioral characteristics of the network in different states, laying a solid foundation for subsequent abnormal behavior detection, and being able to more keenly perceive and respond to potential security threats, thereby achieving a significant improvement in the security of the industrial control network.
[0026] 2. The present invention inputs real-time communication data into the industrial control network intrusion prediction model, outputs the prediction results, and compares the prediction results with various feature data in the industrial control network baseline model. It can quickly identify abnormal communication data that deviates from normal behavior patterns, greatly accelerates the detection speed of potential intrusion behaviors, and ensures that the security team can respond quickly and take corresponding defense measures.
[0027] 3. Through the monitoring mechanism, the present invention can dynamically adjust the monitoring strategy according to the intrusion detection results to ensure that the most effective response measures are taken, which not only improves the emergency response capability, but also provides rich data support for subsequent security strategy optimization; in addition, the automated design of the entire monitoring process, from data extraction, model building to real-time detection and result processing, greatly reduces manual intervention, which not only improves operation and maintenance efficiency, but also significantly reduces security risks and monitoring costs caused by human errors, achieving dual optimization of cost and benefit.
[0028] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0030] Figure 1 is a flow chart of a method for real-time monitoring of industrial control network intrusion according to an exemplary embodiment; Figure 2 is a principle block diagram of a system for real-time monitoring of industrial control network intrusion according to an exemplary embodiment; Figure 3 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION
[0031] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.
[0032] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.
[0033] As used herein, the term "plurality" means two or more than two, unless otherwise specified.
[0034] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.
[0035] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.
[0036] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
[0037] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.
[0038] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.
[0039] Figure 1 An embodiment of a method for real-time monitoring of industrial control network intrusion according to the present invention is shown.
[0040] In this optional embodiment, the method for real-time monitoring of industrial control network intrusion includes: Step S101: extracting characteristic data based on communication data in the industrial control network, and analyzing the characteristic data to establish an industrial control network baseline model; Step S103: integrating the feature data with the machine learning algorithm to construct an industrial control network intrusion prediction model; Step S105: input the real-time communication data into the industrial control network intrusion prediction model, output the prediction result, and combine the prediction result with the industrial control network baseline model to perform intrusion detection on the industrial control network; Step S107: Compare the intrusion detection result with the preset threshold, and formulate a corresponding monitoring mechanism according to the comparison result.
[0041] In this optional embodiment, the extraction of characteristic data based on the communication data in the industrial control network and the analysis of the characteristic data to establish the industrial control network baseline model include: using a network packet capture tool to obtain the communication data in the industrial control network and preprocessing the communication data; using statistical analysis technology to extract characteristic data from the preprocessed communication data, wherein the characteristic data includes network traffic characteristic data, time pattern characteristic data and behavior abnormality characteristic data; using variance analysis and deviation analysis algorithms to analyze the extracted characteristic data and identify communication variables; using an association rule mining algorithm to mine association rules for communication variables and generate communication association rule discovery; combining communication association rule discovery with a hierarchical clustering algorithm to classify the preprocessed communication data; using explanatory analysis technology to analyze various types of communication data, and establishing an industrial control network baseline model based on the analysis results of various types of communication data.
[0042] In this optional embodiment, the combination of communication association rule discovery and hierarchical clustering algorithm to classify the pre-processed communication data includes: based on the results of communication association rule discovery, filtering out communication data for hierarchical clustering analysis; using the filtered communication data as initial clusters, and using the communication similarity formula to calculate the similarity values between the initial clusters; selecting several clusters with the highest similarity values for merging to generate new clusters; repeatedly performing the cluster merging operation until a preset clustering threshold is reached to obtain a clustering result; and according to the clustering result, allocating the pre-processed communication data to each cluster category to obtain a classification of the communication data.
[0043] In this optional embodiment, the communication similarity formula is:
[0044] Where, L m,n represents the similarity value between the mth cluster and the nth cluster in the communication data; C m represents the mth cluster data set in the communication data, C n represents the nth cluster data set in the communication data; J(C m, C n ) indicates C m With C n ; s represents the number of clusters between the mth cluster and the nth cluster in the communication data; ω represents the adjustment parameter; k represents the number of clusters in the communication data; T m represents the similarity coefficient corresponding to the mth cluster in the communication data; T n represents the similarity coefficient corresponding to the nth cluster in the communication data; T k Represents the similarity coefficient between the mth cluster and the nth cluster in the communication data.
[0045] In this optional embodiment, the integration of feature data and machine learning algorithms to construct an industrial control network intrusion prediction model includes: establishing a feature data set based on the extracted feature data, and dividing the feature data set into a training set and a test set; combining the feature data with a random forest algorithm to construct an initial industrial control network intrusion prediction model; using the training set to train the initial industrial control network intrusion prediction model, and evaluating the initial industrial control network intrusion prediction model after training through the test set to obtain the industrial control network intrusion prediction model.
[0046] In this optional embodiment, the formula of the industrial control network intrusion prediction model is:
[0047] Where N represents the industrial control network intrusion prediction value; M represents the number of decision trees in the random forest; f z (x) represents the prediction result of the zth decision tree for the input feature data x.
[0048] In this optional embodiment, the real-time communication data is input into the industrial control network intrusion prediction model, the prediction result is output, and the prediction result is combined with the industrial control network baseline model to perform intrusion detection on the industrial control network, including: collecting real-time communication data in the industrial control network and preprocessing the real-time communication data; extracting real-time feature data from the preprocessed real-time communication data, and inputting the real-time feature data into the industrial control network intrusion prediction model, and outputting the prediction result; according to the industrial control network baseline model, various types of feature data are obtained; the prediction result is compared with various types of feature data, and the data difference is calculated.
[0049] In this optional embodiment, the monitoring mechanism includes an alarm monitoring mechanism and a network monitoring mechanism.
[0050] In this optional embodiment, the intrusion detection result is compared with a preset threshold and a corresponding monitoring mechanism is formulated according to the comparison result, including: comparing the calculated data difference with the preset threshold and judging whether an intrusion has occurred in the industrial control network according to the comparison result; if the data difference is greater than or equal to the preset threshold, an intrusion has occurred in the industrial control network, an alarm monitoring mechanism is activated, and an alarm is sent to the industrial control network administrator; if the data difference is less than the preset threshold, no intrusion has occurred in the industrial control network and the network monitoring mechanism is maintained.
[0051] It should be noted that the alarm monitoring mechanism includes alarm triggering conditions, alarm content, alarm notification methods and alarm processing procedures; among them, the alarm triggering condition is that the data difference is greater than or equal to the preset threshold, and an intrusion has occurred in the industrial control network, at which time the alarm monitoring mechanism will be triggered; the alarm content includes the specific time of intrusion detection, the type of abnormality detected (such as traffic abnormalities, protocol violations, unauthorized access, etc.), and detailed information on abnormal data (such as IP address, port number, data packet content summary, etc.); alarm notification methods include but are not limited to e-mail, SMS, instant message push, system console pop-up window, etc.; the alarm processing procedure includes that after the administrator receives the alarm, he immediately evaluates the alarm content and initiates corresponding emergency response measures, and further investigates and analyzes the abnormal data provided by the alarm to determine the specific circumstances and scope of the intrusion. After handling the intrusion incident, the administrator should record the processing process and results for subsequent security audits and improvements.
[0052] The network monitoring mechanism includes monitoring scope, monitoring frequency, data analysis and reporting, and maintenance and optimization; among them, the monitoring scope should cover all key components and communication links of the industrial control network, including but not limited to network equipment, servers, workstations, PLCs (programmable logic controllers), etc., and the monitoring content should include multiple data sources such as network traffic, equipment status, and security logs; the monitoring frequency is to set a reasonable monitoring frequency based on the actual situation and security requirements of the industrial control network; data analysis and reporting include regular analysis of the collected monitoring data to identify potential security risks and performance bottlenecks, prepare security reports, and report the network security status and potential threats to management and relevant departments; maintenance and optimization include timely adjustment and optimization of monitoring strategies based on monitoring results and security reports to improve the accuracy and efficiency of monitoring, and regular maintenance and upgrades of the monitoring system to ensure its stability and reliability.
[0053] Figure 2 An embodiment of a system for real-time monitoring of industrial control network intrusion according to the present invention is shown.
[0054] In this optional embodiment, the system for real-time monitoring of industrial control network intrusion includes: The industrial control network baseline model establishment module 201 is used to extract characteristic data based on the communication data in the industrial control network, and analyze the characteristic data to establish the industrial control network baseline model; The industrial control network intrusion prediction model building module 203 is used to integrate the feature data with the machine learning algorithm to build an industrial control network intrusion prediction model; The industrial control network intrusion detection module 205 is used to input the real-time communication data into the industrial control network intrusion prediction model, output the prediction result, and combine the prediction result with the industrial control network baseline model to perform intrusion detection on the industrial control network; The intrusion detection result processing module 207 is used to compare the intrusion detection result with a preset threshold value and formulate a corresponding monitoring mechanism according to the comparison result.
[0055] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network 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, the steps in the above method embodiment are implemented.
[0056] Those skilled in the art will 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 invention, and does not constitute a limitation on the computer device to which the solution of the present invention 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.
[0057] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.
[0058] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.
[0059] 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 memory, storage, database or other media used in the embodiments provided by the present invention 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 or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0060] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.
Claims
1. A method for real-time monitoring of industrial control network intrusion, characterized in that: include: Extract characteristic data based on the communication data in the industrial control network, and analyze the characteristic data to establish the industrial control network baseline model; Integrate feature data with machine learning algorithms to build an industrial control network intrusion prediction model; Input the real-time communication data into the industrial control network intrusion prediction model, output the prediction results, and combine the prediction results with the industrial control network baseline model to perform intrusion detection on the industrial control network; Compare the intrusion detection results with the preset thresholds, and formulate corresponding monitoring mechanisms based on the comparison results.
2. A method for real-time monitoring of industrial control network intrusion according to claim 1, characterized in that: The extracting characteristic data according to the communication data in the industrial control network and analyzing the characteristic data to establish the industrial control network baseline model includes: Use network packet capture tools to obtain communication data in the industrial control network and pre-process the communication data; Extracting characteristic data from the preprocessed communication data using statistical analysis technology, wherein the characteristic data includes network traffic characteristic data, time pattern characteristic data and behavior abnormality characteristic data; Variance analysis and deviation analysis algorithms are used to analyze the extracted feature data and identify communication variables; Use association rule mining algorithm to mine the communication variables and generate communication association rule discovery; Combining communication association rule discovery with hierarchical clustering algorithm, the pre-processed communication data is classified; Explanatory analysis techniques are used to analyze various types of communication data, and an industrial control network baseline model is established based on the analysis results of various types of communication data.
3. A method for real-time monitoring of industrial control network intrusion according to claim 2, characterized in that: The method of combining communication association rule discovery with a hierarchical clustering algorithm to classify the pre-processed communication data includes: Based on the results of communication association rule discovery, the communication data for hierarchical clustering analysis is screened out; The filtered communication data is used as the initial clustering, and the similarity values between the initial clusters are calculated using the communication similarity formula; Select several clusters with the highest similarity values to merge and generate new clusters; Repeat the clustering merging operation until the preset clustering threshold is reached to obtain the clustering result; According to the clustering results, the preprocessed communication data is allocated to each cluster category to obtain the classification of the communication data.
4. A method for real-time monitoring of industrial control network intrusion according to claim 3, characterized in that: The communication similarity formula is: Where, L m,n represents the similarity value between the mth cluster and the nth cluster in the communication data; C m represents the mth cluster data set in the communication data, C n represents the nth cluster data set in the communication data; J(C m, C n ) indicates C m With C n ; s represents the number of clusters between the mth cluster and the nth cluster in the communication data; ω represents the adjustment parameter; k represents the number of clusters in the communication data; T m represents the similarity coefficient corresponding to the mth cluster in the communication data; T n represents the similarity coefficient corresponding to the nth cluster in the communication data; T k Represents the similarity coefficient between the mth cluster and the nth cluster in the communication data.
5. A method for real-time monitoring of industrial control network intrusion according to claim 1, characterized in that: The integration of feature data and machine learning algorithms to construct an industrial control network intrusion prediction model includes: According to the extracted feature data, a feature data set is established, and the feature data set is divided into a training set and a test set; Combine feature data with random forest algorithm to build an initial industrial control network intrusion prediction model; The training set is used to train the initial industrial control network intrusion prediction model, and the test set is used to evaluate the initial industrial control network intrusion prediction model after training to obtain the industrial control network intrusion prediction model.
6. A method for real-time monitoring of industrial control network intrusion according to claim 5, characterized in that: The formula of the industrial control network intrusion prediction model is: Where N represents the industrial control network intrusion prediction value; M represents the number of decision trees in the random forest; f z (x) represents the prediction result of the zth decision tree for the input feature data x.
7. A method for real-time monitoring of industrial control network intrusion according to claim 1, characterized in that: The step of inputting the real-time communication data into the industrial control network intrusion prediction model, outputting the prediction result, and combining the prediction result with the industrial control network baseline model to perform intrusion detection on the industrial control network includes: Collect real-time communication data within the industrial control network and pre-process the real-time communication data; Extracting real-time feature data from the pre-processed real-time communication data, and inputting the real-time feature data into the industrial control network intrusion prediction model, and outputting the prediction result; Obtain various feature data based on the industrial control network baseline model; Compare the prediction results with various feature data and calculate the data difference.
8. A method for real-time monitoring of industrial control network intrusion according to claim 1, characterized in that: The monitoring mechanism includes an alarm monitoring mechanism and a network monitoring mechanism.
9. A method for real-time monitoring of industrial control network intrusion according to claim 8, characterized in that: The step of comparing the intrusion detection result with a preset threshold and formulating a corresponding monitoring mechanism according to the comparison result includes: The calculated data difference is compared with the preset threshold, and whether the industrial control network is invaded is determined based on the comparison result; If the data difference is greater than or equal to the preset threshold, the industrial control network is invaded, the alarm monitoring mechanism is activated, and the alarm is sent to the industrial control network administrator; If the data difference is less than the preset threshold, there is no intrusion in the industrial control network and the network monitoring mechanism continues.
10. A system for real-time monitoring of industrial control network intrusion, characterized in that: include: The industrial control network baseline model establishment module is used to extract characteristic data based on the communication data in the industrial control network, and analyze the characteristic data to establish the industrial control network baseline model; Industrial control network intrusion prediction model building module, which is used to integrate feature data with machine learning algorithms to build an industrial control network intrusion prediction model; The industrial control network intrusion detection module is used to input real-time communication data into the industrial control network intrusion prediction model, output the prediction results, and combine the prediction results with the industrial control network baseline model to perform intrusion detection on the industrial control network; The intrusion detection result processing module is used to compare the intrusion detection result with the preset threshold value and formulate a corresponding monitoring mechanism according to the comparison result.
Citation Information
Cited By
Industrial control system intrusion detection method and system based on Mama model
CN119848749A
