A data security prevention method for abnormal access detection in industrial control networks

Through process chain grid model and attack library simulation technology, the problem of insufficient abnormal access detection effect of industrial control network is solved, and more accurate abnormal traffic detection and false alarm rate reduction is achieved, meeting the network security needs of intelligent manufacturing.

CN118449775BActive Publication Date: 2024-11-08GUANGXI POWER GRID CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410728935.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-06
Publication Date
2024-11-08
Estimated Expiration
2044-06-06

AI Technical Summary

Technical Problem

The existing industrial control network abnormal access detection technology is insufficient in terms of process correlation, making it difficult to effectively detect abnormal access, resulting in a high false alarm rate and cannot meet the network security needs of intelligent manufacturing.

Method used

The process chain grid model is used for abnormal access detection. By establishing a mapping model with the industrial control network, monitoring the operating data and transmission routes of production equipment, identifying abnormal intrusion clues, conducting attack traceability analysis and protection, and using the attack library for simulation and Protect tool settings to reduce false alarm rate.

Benefits of technology

It improves the accuracy and efficiency of abnormal flow detection, reduces the false alarm rate, and ensures the safety and production order of the industrial control network.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118449775B_ABST
    Figure CN118449775B_ABST
Patent Text Reader

Abstract

The present invention is applicable to the field of network security technology, and provides a data security prevention method for data security prevention of abnormal access detection in an industrial control network, the method comprising: establishing a process chain grid model mapped with the industrial control network; performing real-time operation monitoring of the industrial control network, recording the operation data of each controller and its transmission route; establishing a twin route for the transmission route in the process chain grid model, if there is at least one group of twin routes that cannot match the known connection link, then marking the transmission route twinned with the group of twin routes as an abnormal intrusion clue; performing attack source tracing analysis on the abnormal intrusion clue, and performing intrusion attack source tracing filtering. The method provided by the present invention adopts grid simulation and monitoring for each controller connected to the industrial control network, realizes mapping associated with the process through monitoring of grid nodes and connection links, better extracts and analyzes the correlation between abnormal features in network traffic data, and realizes high-performance detection of abnormal network traffic.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of network security, and in particular relates to a data security prevention method for abnormal access detection in an industrial control network. Background Art

[0002] With the rapid development of network information technology, industrial control networks play an increasingly important role in industrial production. However, the security issues of industrial control networks (also known as industrial control networks) are becoming increasingly prominent. Abnormal access may lead to serious consequences such as production accidents and data leakage.

[0003] In order to avoid abnormal attacks, some existing industrial control networks adopt isolation, that is, only use local area networks in production workshops without connecting to the Internet; however, this method is increasingly unable to adapt to intelligent manufacturing; there are also existing anomaly detection technologies that use machine learning-based methods to detect network attacks, which have been widely studied due to their simplicity and efficiency. Although these machine learning-based algorithms have achieved good performance in data security prevention of abnormal access detection in industrial control networks, they are still insufficient in terms of process association.

[0004] Therefore, how to effectively detect abnormal access in industrial control networks has become an important research direction in the current network security field. To this end, the present invention provides a data security prevention method for abnormal access detection in industrial control networks. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a data security prevention method for abnormal access detection in an industrial control network, so as to achieve more accurate extraction of abnormal flow characteristics and improve the effect in process correlation, aiming to further improve the effective detection rate of existing abnormal flow detection methods, reduce the false alarm rate, and ensure good production order.

[0006] The embodiment of the present invention is implemented as follows: a data security prevention method for abnormal access detection in an industrial control network, the method comprising the following steps:

[0007] Establish a process chain grid model mapped with the industrial control network; in the process chain grid model, each grid node corresponds to a controller of a production equipment, and the connection links between the grid nodes represent the process association rules that each controller follows to communicate with the process chain;

[0008] Conduct real-time operation monitoring of the industrial control network and record the operation data of each controller and its transmission route;

[0009] The transmission routes are twinned in the process chain grid model. If there is at least one set of twin routes that cannot match the known connection links, the transmission routes that are twinned with the set of twin routes are marked as abnormal intrusion clues.

[0010] Conduct attack source tracing analysis on the abnormal intrusion clues, perform intrusion attack source tracing filtering, locate the intruded target controller, and protect the target controller.

[0011] Furthermore, the method further comprises:

[0012] Use the attack tools in the attack library to simulate an intrusive attack on the industrial control network;

[0013] Monitoring the amplification degree of the connection links in the process chain grid model, and marking the connection links whose amplification degree exceeds a first amplification threshold and the currently used attack tool;

[0014] Set corresponding protection tools for the marked connection links.

[0015] Furthermore, when establishing the process chain grid model, the method further includes:

[0016] Obtain energy consumption data of each production equipment and control data of the corresponding controller, perform data preprocessing on the acquired energy consumption data and control data to obtain data samples;

[0017] Mining frequent item sets between data in data samples and generating association rules for the frequent item sets;

[0018] Optimizing the association rules of the frequent item sets to obtain an optimal rule set;

[0019] The connection links of each network node are determined and connected according to the optimal rule set.

[0020] Furthermore, the Apriori algorithm is used to mine frequent item sets between data in the data sample.

[0021] Furthermore, the step of establishing a process chain grid model mapped with the industrial control network specifically includes:

[0022] Obtain relevant parameters of all production equipment, including name, process, communication address and communication type;

[0023] Based on the standardized grid, the controllers of each production equipment are loaded as grid nodes in the standardized grid;

[0024] Based on the production process of the archived products, determine the production process relationship between production equipment, obtain process association rules, and establish a process chain;

[0025] According to the process chain, connection links between grid nodes are connected.

[0026] Furthermore, the steps of performing real-time operation monitoring of the industrial control network and recording the operation data of each controller and its transmission route specifically include:

[0027] Conduct real-time operation monitoring of industrial control networks and generate operation monitoring information;

[0028] According to the operation monitoring information, a chain of command generation and response between the industrial control network and the controller, and between the controllers is created;

[0029] Record the operating data of each controller;

[0030] The command generation and response chain is monitored, and a transmission route of the operation data is determined based on the monitoring data.

[0031] Furthermore, the method further comprises:

[0032] After locating the intruded target controller, query the controllers of the upstream and downstream chains of the target controller;

[0033] Determine whether to implement isolation control on the controllers of the upstream and downstream chains based on the query results.

[0034] Another object of the embodiment of the present invention is to provide a data security prevention system for abnormal access detection of industrial control networks, which is used in the data security prevention method for abnormal access detection of industrial control networks as described above, and the system includes: a model building module, a traffic monitoring module, a link matching and marking module, and an attack source analysis and processing module;

[0035] The model building module is used to establish a process chain grid model mapped with the industrial control network; in the process chain grid model, each grid node corresponds to a controller of a production equipment, and the connection links between the grid nodes represent the process association rules for each controller to follow the process chain for communication links;

[0036] The flow monitoring module is used to monitor the real-time operation of the industrial control network and record the operation data of each controller and its transmission route;

[0037] The link matching and marking module is used to establish twin routes for transmission routes in the process chain grid model. If there is at least one set of twin routes that cannot match the known connection links, the transmission routes that are twinned with the set of twin routes are marked as abnormal intrusion clues;

[0038] The attack source analysis and processing module is used to perform attack source tracing analysis on the abnormal intrusion clue, perform intrusion attack source tracing filtering, locate the intruded target controller, and protect the target controller.

[0039] Furthermore, the system also includes: an invasive attack simulation module, an amplification degree monitoring module and a distributed protection module;

[0040] The invasive attack simulation module can use the attack tools in the attack library to simulate invasive attacks on the industrial control network;

[0041] The amplification degree monitoring module is used to monitor the amplification degree of the connection links in the process chain grid model, and mark the connection links whose amplification degree exceeds the first amplification threshold and the currently used attack tool;

[0042] The distributed protection module is used to set corresponding protection tools for the marked connection links.

[0043] Another object of an embodiment of the present invention is to provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor executes the steps of the data security prevention method for abnormal access detection in the industrial control network.

[0044] An embodiment of the present invention provides a data security prevention method for abnormal access detection in an industrial control network. The method adopts grid simulation and monitoring for each controller connected to the industrial control network, realizes mapping associated with the process through monitoring of grid nodes and connection links, better extracts and analyzes the correlation between abnormal features in network traffic data, realizes high-performance detection of abnormal network traffic, effectively classifies normal traffic and abnormal traffic, extracts and analyzes the correlation between features in network traffic data, thereby more accurately realizing high-performance detection of abnormal network traffic, improving detection efficiency and reducing false alarm rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flow chart of a data security prevention method for abnormal access detection in an industrial control network provided by an embodiment of the present invention;

[0046] Figure 2 This is a first sub-flow chart of the data security prevention method for abnormal access detection in the industrial control network according to an embodiment of the present invention;

[0047] Figure 3 It is a second sub-flow chart of the data security prevention method for abnormal access detection in the industrial control network according to an embodiment of the present invention;

[0048] Figure 4 It is a third sub-flow chart of the data security prevention method for abnormal access detection in the industrial control network in an embodiment of the present invention;

[0049] Figure 5 This is a fourth sub-flow chart of the data security prevention method for abnormal access detection in an industrial control network according to an embodiment of the present invention;

[0050] Figure 6 The fifth sub-flow chart of the data security prevention method for abnormal access detection in the industrial control network according to the embodiment of the present invention;

[0051] Figure 7 A framework structure of a data security prevention system for abnormal access detection in an industrial control network provided by an embodiment of the present invention Figure 1 ;

[0052] Figure 8 A framework structure of a data security prevention system for abnormal access detection in an industrial control network provided by an embodiment of the present invention Figure 2 ;

[0053] Fig. 9 A framework structure diagram of a flow monitoring module provided by an embodiment of the present invention;

[0054] Fig.10 1 is a block diagram of the internal structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0056] In one embodiment, a data security prevention method for abnormal access detection in an industrial control network is mainly applied at the control network level of the industrial control network. The industrial control network is a comprehensive integrated network involving computer technology, communication technology, control technology, and field bus technology. In terms of function, the industrial control network can be divided into: information network and control network. The information network processes the management and decision-making information of the industrial control system and is located in the middle and upper layers of the industrial control network; the control network processes the real-time measurement and control information of the control site and is located in the middle and lower layers of the industrial control network; the control network is mainly built based on the field bus and is mainly used for automatic control of production equipment and detection and monitoring of the production process status; the control network not only sends the equipment operation parameters, status, and fault information of the production site to the control center, but also sends various control, maintenance, configuration and other commands to the field bus; at the same time, the control network also plays a role in data connection and information sharing with the operation terminal and the upper management information network. In addition, in intelligent manufacturing, the field bus is implemented using an open control network technology that complies with international standards, and maintains a connection with the external Internet. Its network security is related to production safety and even involves commercial secrets.

[0057] Figure 1 The workflow diagram of a data security prevention method for abnormal access detection in an industrial control network provided by an embodiment of the present invention may specifically include the following steps S101-S104:

[0058] S101, establishing a process chain grid model mapped with the industrial control network; in the process chain grid model, each grid node corresponds to a controller of a production device, and the connection links between the grid nodes represent the process association rules that each controller follows to communicate with the process chain;

[0059] In this step, the process chain grid model and the control center of the industrial control network can be built in the back-end server. The mapping between the industrial control network and the process chain grid model, that is, the process chain grid model is a digital twin network of the industrial control network; the digital twin network can reflect the control, response and bus connection relationship of the industrial control network.

[0060] For example, in the production process of PVB products: the multi-process production process relies on process production, and the product quality status is affected by various factors in the production process. The processes are linked and interconnected. For the extended production equipment of each process, if we want to avoid the impact of network intrusion on the quality of a certain process and the expansion of the impact, we must not only prevent the controller involved in this process from becoming an element of the affected quality, but also avoid the influence of the controllers corresponding to the previous and subsequent processes on this process. Therefore, in the face of products in the multi-process production stage, the network protection problem of its production equipment, in order to avoid the expansion of the associated impact, we must fully understand the entire process of product manufacturing and master the connection between the processes to achieve better protection.

[0061] In an example of this embodiment, Figure 3 As shown, when establishing the process chain grid model, the method further includes:

[0062] S301, obtaining energy consumption data of each production equipment and control data of the corresponding controller, performing data preprocessing on the obtained energy consumption data and control data to obtain data samples;

[0063] The energy consumption data can be obtained through a digital meter or other equipment, and the control data of the controller can be obtained through a data bus connected to the controller;

[0064] The above-mentioned preprocessing methods include but are not limited to data cleaning, data integration, data transformation, data reduction, etc. Since data preprocessing belongs to the existing technology, it will not be described in detail here.

[0065] S302, mining frequent item sets between data in the data sample, and generating association rules of the frequent item sets;

[0066] Generally, the Apriori algorithm can be used to mine frequent item sets between data in a data sample; it should be noted that the Apriori algorithm is an existing technology and will not be described in detail here.

[0067] S303, optimizing the association rules of the frequent itemsets to obtain an optimal rule set;

[0068] Among them, optimization processing: K-Means clustering algorithm and particle swarm optimization algorithm (PSO optimization algorithm for short) can be used;

[0069] S304, determining the connection links of each network node according to the optimal rule set and connecting them;

[0070] Each network node represents a controller of a production device, and the connection links between the network nodes represent the communication between the controllers. Moreover, the specific interaction of this communication corresponds to the production process of the product.

[0071] S102, perform real-time operation monitoring of the industrial control network and record the operation data of each controller and its transmission route;

[0072] In this step, if Figure 5 As shown, in one scenario, step S102 specifically includes:

[0073] S501, perform real-time operation monitoring of the industrial control network and generate operation monitoring information;

[0074] S502, creating a command generation and response chain between the industrial control network and the controller, and between each controller according to the operation monitoring information;

[0075] Among them, the instruction generation and response chain loop is a transmission route of an instruction. Some transmission routes are closed-loop, that is, some chains have only instruction generation and delivery, and no feedback or response after the instruction is executed; some transmission routes are unidirectional, that is, some chains have instruction generation and delivery, and also feedback or response after the instruction is executed, forming a closed loop; the specific needs need to be determined according to the specific process of producing the product.

[0076] S503, recording the operation data of each controller;

[0077] The above-mentioned operating data can be recorded by a flow monitoring unit connected to the bus, specifically a flow monitor;

[0078] S504, monitor the instruction generation and response chain, and determine the transmission route of the operation data according to the monitoring data.

[0079] In one example of this embodiment, Figure 1 In the method, the method further comprises:

[0080] S103, establishing twin routes for the transmission routes in the process chain grid model. If there is at least one set of twin routes that cannot match the known connection links, then mark the transmission routes that are twins of the set of twin routes as abnormal intrusion clues;

[0081] For example: if it is a single-point invasion, there may be only one twin route generated;

[0082] In case of multi-point intrusion, multiple twin routes may be generated; however, the twin routes will not match the known connection links;

[0083] At the same time, the analysis of recorded operation data can further help identify abnormal intrusion clues;

[0084] Among them, the known connection links are the connection links that have been connected in the process chain grid model.

[0085] In addition, the recorded operation data can also be analyzed separately to identify abnormal intrusion clues.

[0086] S104: Perform attack source tracing analysis on the abnormal intrusion clue, perform intrusion attack source tracing filtering, locate the intruded target controller, and protect the target controller.

[0087] Protect the target controller, including marking the source tracing attack website, configuring access detection policy, setting the source tracing attack website as a blocking site, and implementing filtering and shielding of the source tracing attack website.

[0088] For example: when there is an attack, the corresponding controller has a record of accessing an external website at the corresponding time, and the URL of the website will be sent to the KServices server for query, and classification information will be returned. If there is any access behavior, it will be detected and an alarm will be generated.

[0089] In one embodiment, Figure 2 As shown, the method also includes:

[0090] S201, using the attack tools in the attack library to simulate an intrusive attack on the industrial control network;

[0091] S202, monitoring the amplification degree of the connection links in the process chain grid model, and marking the connection links whose amplification degree exceeds a first amplification threshold and the currently used attack tool;

[0092] Generally, the communication capacity T of the connection link can be set with a communication threshold. For example, in the SS7 signaling system, the data transmission capacity of a link is calculated as 40% T of its actual capacity.

[0093] Therefore, when the amplification degree of the connection link exceeds the first amplification threshold (ie, 40% T), the connection link and the currently used attack tool are marked.

[0094] S203, setting a corresponding protection tool for the marked connection link;

[0095] In a scenario, the functions of the protection tool include: resetting, expanding capacity, increasing transmission delay, discarding subsequent data to be transmitted, etc. The protection tool is a computer program or program fragment;

[0096] By setting protection measures for individual controllers, distributed control can be achieved, avoiding the impact of protecting the entire industrial control network on other normal control and management production and reducing production efficiency.

[0097] In step S201, the attack library is pre-established with more than 7,000 attack tools built in, and supports the update of attack tools to ensure the regular detection of the latest attack methods, supporting overflow attacks, brute force attacks, backdoor attacks, CGI attacks, SQL injection attacks, Webshell attacks, cross-site scripting attacks, scanning attacks, cross-site request forgery attacks, distributed denial of service attacks and other anomaly detection.

[0098] In one embodiment, Figure 4 As shown, the steps of establishing a process chain grid model mapped with the industrial control network specifically include:

[0099] S401, obtaining relevant parameters of all production equipment, the relevant parameters including name, process, communication address and communication type;

[0100] Taking the multi-process flexible production of PVB products as an example, the names and processes of related parameters are as follows: the processes include feeding, dissolving, condensing, heating, heat preservation, washing, stabilization, etc.; corresponding to feeders, dissolvers, condensers, heating devices, heat preservation devices, water washers, stabilizers, etc.; involving PVA feeding amount, heating start temperature / end temperature, jacket temperature, heating rate plate washing liquid level, phase change temperature, butyraldehyde feeding amount, aldehyde feeding temperature, setting of frequency before / mid / after aldehyde feeding, heating maximum temperature, heat preservation second maximum temperature, first / second / third reuse water washing times, first / second / third reuse water starting time temperature, ice pure water washing times, quality test indicators, etc. In this way, the process chain of PVB product production can be sorted out by analyzing the process data of these processes and the inherent relationship between the communication address and communication type between the controllers corresponding to the process data.

[0101] S402, based on the standardized grid, loading the controller of each production equipment into the standardized grid as a grid node;

[0102] Among them, the standardized grid is the framework for computer programs to model digital twin models, which is a direct application of existing technologies;

[0103] S403, based on the production process of the archived product, determine the production process relationship between the production equipment, obtain the process association rules, and establish the process chain;

[0104] As mentioned above, the intrinsic relationship between the process data of these processes, the communication addresses and communication types between the controllers corresponding to the process data can be determined and recorded by those skilled in the art, that is, the recorded data constitutes the production process of the documented product to establish the process chain;

[0105] S404: Connect the connection links between the grid nodes according to the process chain.

[0106] In one embodiment, Figure 6 As shown, the method also includes:

[0107] S601, after locating the intruded target controller, query the controllers of the upstream and downstream chains of the target controller;

[0108] On the one hand, this query can pre-set response conditions to ensure that the single-point intrusion of the controller does not affect other controllers according to the response situation;

[0109] On the other hand, this query can verify whether the connection between the upstream and downstream controllers of the target controller is normal.

[0110] S602: Determine whether to implement isolation control on the controllers of the upstream and downstream chains according to the query result.

[0111] like Figure 7 As shown, in one embodiment, a data security prevention system for abnormal access detection of an industrial control network is used for the data security prevention method for abnormal access detection of an industrial control network as described above, and the system includes: a model building module 100, a traffic monitoring module 200, a link matching and marking module 300, and an attack source analysis and processing module 400;

[0112] The model building module 100 is used to establish a process chain grid model mapped with the industrial control network; in the process chain grid model, each grid node corresponds to a controller of a production device, and the connection links between the grid nodes represent the process association rules for each controller to follow the process chain for communication links;

[0113] The flow monitoring module 200 is used to monitor the real-time operation of the industrial control network and record the operation data of each controller and its transmission route;

[0114] The link matching and marking module 300 is used to establish twin routes for transmission routes in the process chain grid model. If there is at least one set of twin routes that cannot match the known connection links, the transmission routes that are twinned with the set of twin routes are marked as abnormal intrusion clues;

[0115] The attack source analysis and processing module 400 is used to perform attack source tracing analysis on the abnormal intrusion clue, perform intrusion attack source tracing filtering, locate the intruded target controller, and protect the target controller.

[0116] In an example of this embodiment, Figure 8 As shown, the system further includes: an invasive attack simulation module 500, an expansion degree monitoring module 600 and a distributed protection module 700;

[0117] The invasive attack simulation module 500 can use the attack tools in the attack library to simulate invasive attacks on the industrial control network;

[0118] The amplification degree monitoring module 600 is used to monitor the amplification degree of the connection links in the process chain grid model, and mark the connection links whose amplification degree exceeds the first amplification threshold and the currently used attack tool;

[0119] The distributed protection module 700 is used to set corresponding protection tools for the marked connection links.

[0120] In an example of this embodiment, Fig. 9 As shown, the flow monitoring module 200 includes: a flow monitoring unit 210, a monitoring information processing unit 220, an operation data recording unit 230 and a transmission trace determination unit 240;

[0121] The flow monitoring unit 210 is used to perform real-time operation monitoring of the industrial control network and generate operation monitoring information;

[0122] The monitoring information processing unit 220 can create a command generation and response chain between the industrial control network and the controller, and between each controller according to the operation monitoring information;

[0123] Among them, the instruction generation and response chain loop is a transmission route of an instruction. Some transmission routes are closed-loop, that is, some chains have only instruction generation and delivery, and no feedback or response after the instruction is executed; some transmission routes are unidirectional, that is, some chains have instruction generation and delivery, and also feedback or response after the instruction is executed, forming a closed loop; the specific needs need to be determined according to the specific process of producing the product.

[0124] The operation data recording unit 230 is used to record the operation data of each controller;

[0125] The above-mentioned operating data can be recorded by a flow monitoring unit connected to the bus, specifically a flow monitor;

[0126] The transmission trace determination unit 240 is used to monitor the instruction generation and response chain, and determine the transmission route of the operation data according to the monitoring data.

[0127] In this embodiment, the control traffic (i.e., operating data) can be monitored by a traffic monitor, and the control traffic can be extracted to obtain control process data as sample data to perform data security prevention for abnormal access detection in the industrial control network. During abnormality detection, some features that can characterize network abnormalities can be extracted and analyzed, such as abnormal source IP addresses or access ports.

[0128] In addition, an attention mechanism can be trained through sample data. The trained attention mechanism can be regarded as a neural network model. Through this neural network model, learning can be used to control the correlation between traffic features, redraw the instruction generation and response chain, and then obtain features or feature vectors that can better reflect network anomalies, thereby extracting more accurate traffic features, and then achieving high-performance detection of abnormal network traffic and improving detection efficiency.

[0129] In this embodiment, an embodiment of the present invention provides a data security prevention method for abnormal access detection in an industrial control network. The method uses a process chain grid model mapped to the industrial control network, adopts grid simulation and monitoring, and realizes mapping associated with the process through monitoring of grid nodes and connection links, so as to better extract and analyze the correlation between abnormal features in network traffic data, realize high-performance detection of abnormal network traffic, effectively classify normal traffic and abnormal traffic, extract and analyze the correlation between features in network traffic data, thereby more accurately realizing high-performance detection of abnormal network traffic and improving detection efficiency.

[0130] In one embodiment, a computer device is provided, which includes a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of the data security prevention method for abnormal access detection in the industrial control network.

[0131] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor executes the steps of the data security prevention method for abnormal access detection in an industrial control network.

[0132] Fig.10 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may specifically be a terminal (or a server). Fig.10As shown, the computer device includes a processor, a memory, a network interface, an input device and a display screen connected through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement a data security prevention method for abnormal access detection of an industrial control network. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can execute a data security prevention method for abnormal access detection of an industrial control network. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0133] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0134] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0135] 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 program can be stored in a non-volatile computer-readable storage medium. When the 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 in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0136] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0137] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0138] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A data security prevention method for abnormal access detection in industrial control networks, characterized in that: The method comprises the following steps: Establish a process chain grid model mapped with the industrial control network; in the process chain grid model, each grid node corresponds to a controller of a production equipment, and the connection links between the grid nodes represent the process association rules that each controller follows to communicate with the process chain; Conduct real-time operation monitoring of the industrial control network and record the operation data of each controller and its transmission route; The transmission routes are twinned in the process chain grid model. If there is at least one set of twin routes that cannot match the known connection links, the transmission routes that are twinned with the set of twin routes are marked as abnormal intrusion clues. Conduct attack source tracing analysis on the abnormal intrusion clues, perform intrusion attack source tracing filtering, locate the intruded target controller, and protect the target controller; The step of establishing a process chain grid model mapped with the industrial control network specifically includes: Obtain relevant parameters of all production equipment, including name, process, communication address and communication type; Based on the standardized grid, the controllers of each production equipment are loaded as grid nodes in the standardized grid; Based on the production process of the archived products, determine the production process relationship between production equipment, obtain process association rules, and establish a process chain; According to the process chain, connecting links between grid nodes; The steps of performing real-time operation monitoring of the industrial control network and recording the operation data of each controller and its transmission route specifically include: Conduct real-time operation monitoring of industrial control networks and generate operation monitoring information; According to the operation monitoring information, a chain of command generation and response between the industrial control network and the controller, and between the controllers is created; Record the operating data of each controller; The command generation and response chain is monitored, and a transmission route of the operation data is determined based on the monitoring data.

2. The method according to claim 1, characterized in that The method further comprises: Use the attack tools in the attack library to simulate an intrusive attack on the industrial control network; Monitoring the amplification degree of the connection links in the process chain grid model, and marking the connection links whose amplification degree exceeds a first amplification threshold and the currently used attack tool; Set corresponding protection tools for the marked connection links.

3. The method according to claim 1, characterized in that When establishing the process chain grid model, the method further includes: Obtain energy consumption data of each production equipment and control data of the corresponding controller, perform data preprocessing on the acquired energy consumption data and control data to obtain data samples; Mining frequent item sets between data in data samples and generating association rules for the frequent item sets; Optimizing the association rules of the frequent item sets to obtain an optimal rule set; The connection links of each network node are determined and connected according to the optimal rule set.

4. The method according to claim 3, characterized in that Apriori algorithm is used to mine frequent itemsets between data in data samples.

5. The method according to claim 1, characterized in that The method further comprises: After locating the intruded target controller, query the controllers of the upstream and downstream chains of the target controller; Determine whether to implement isolation control on the controllers of the upstream and downstream chains based on the query results.