Asset identification and risk early warning method and system for industrial control system

By establishing an asset and vulnerability risk information database and remote login using the containment protocol, combining rough matching and fine matching to identify asset information, the integration of asset identification and risk warning in the existing technology is solved, and the accurate identification and real-time identification of the industrial control system is achieved. Risk warning improves system security.

CN119094155APending Publication Date: 2024-12-06NANJING NARI NETWORK SECURITY TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411033547.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Existing asset identification and risk warning technologies cannot efficiently integrate asset information between multiple industrial control systems, resulting in asset missed identification and risk vulnerabilities in old version applications that cannot be updated in time, thereby increasing the risk of industrial control systems being attacked.

Method used

By establishing an asset and vulnerability risk information database, remotely logging into the target host using the Container Protocol for asset scanning, identifying asset information in combination with rough matching and fine matching, determining whether there is a vulnerability risk in the device version number, and issuing early warnings and updates.

Benefits of technology

It realizes accurate identification of industrial control system assets and real-time risk warning, ensures system security, helps managers make smarter decisions, and improves the security and sustainable development foundation of industrial control networks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119094155A_ABST
    Figure CN119094155A_ABST
Patent Text Reader

Abstract

The invention discloses an industrial control system asset identification and risk early warning method and system. The method comprises the following steps: pre-establishing an asset and vulnerability risk information base according to key information of an industrial control system; a target host is remotely logged in through a containment protocol for asset scanning, and asset information of each target industrial control device is actively detected; performing matching identification on the scanned assets in a mode of combining rough matching and fine matching; and after the application asset version number of the target equipment is identified, judging whether the asset information has a vulnerability risk, and if the vulnerability risk is found, sending out an early warning and updating the application. According to the invention, the problems of large asset scale, difficult identification and untimely risk early warning of the industrial control system are solved, and the asset identification and risk early warning capability of the industrial control system is effectively improved; based on the active asset identification and risk early warning technology, the asset updating change can be accurately identified, and it is ensured that the asset identification of the industrial control system is accurate and correct and the risk early warning is timely and effective.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of automated network security technology, and in particular to an industrial control system asset identification and risk early warning method and system. Background Art

[0002] As industrial information technology has been developing for many years, a large number of business systems, operating systems, application components and other version iterations have appeared in industrial control systems to meet various functional requirements. Due to the application of modern information technologies such as artificial intelligence, blockchain, and big data in industrial control systems, various types of terminal devices in industrial control systems have exploded, resulting in a significant increase in asset information, and the accuracy of asset identification and the real-time requirements for risk warnings are getting higher and higher.

[0003] Traditional asset identification and risk warning business systems can no longer meet the requirements, and are prone to forming information islands, resulting in a mismatch between actual asset information and system storage information; if there is a situation where vulnerability patches are not timely, risk information needs to be promptly warned, otherwise it is easy for the industrial control system to be attacked, causing adverse effects. Since existing asset identification and risk warning technologies cannot efficiently integrate asset information between multiple industrial control systems, it is easy to cause asset misidentification, and old versions of related applications have risk vulnerabilities and cannot be updated in time. The present invention is based on active asset identification and risk warning technology, which is conducive to integrating asset information in various devices in the industrial control network, accurately identifying asset updates and changes, and ensuring that the identification of assets in the industrial control system is accurate and the risk warning is timely and effective. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an industrial control system asset identification and risk warning method and system to solve the problem that the existing asset identification and risk warning technology cannot efficiently integrate the asset information between multiple industrial control systems, which easily leads to asset misidentification and the old versions of related applications have risk vulnerabilities and cannot be updated in time.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, the present invention provides an industrial control system asset identification and risk warning method, including: pre-establishing an asset and vulnerability risk information database based on key information of the industrial control system; remotely logging into the target host through the secure shell protocol to perform asset scanning, and actively detecting the asset information of each target industrial control device; matching and identifying the scanned assets by combining coarse matching and fine matching; after identifying the application asset version number of the target device, determining whether the asset information has a vulnerability risk, and if the vulnerability risk is found, issuing a warning and performing an application update.

[0008] As a preferred solution of the industrial control system asset identification and risk warning method of the present invention, the establishment of the asset and vulnerability risk information database includes:

[0009] Pre-establish an asset and vulnerability risk information library based on key information of the industrial control system, where the key information of the industrial control system includes device IP address, application name and version number, number of application system files, application system file hash value, and application vulnerability information;

[0010] The device IP address, application name and version number, application system file quantity, and application system file hash value are used for asset matching to jointly determine the version number of each target industrial control device application;

[0011] When the application version of each target industrial control device is updated, the vulnerability risks existing in the old version are actively added to the asset and vulnerability risk information library.

[0012] As a preferred solution of the industrial control system asset identification and risk warning method of the present invention, the rough matching process includes:

[0013] According to the established asset and vulnerability risk information database, each industrial control device is divided into asset partitions. One target industrial control device corresponds to one asset and vulnerability risk information database table. Different applications on each target industrial control device are distinguished by version name and version number.

[0014] In the rough matching stage, if there is less asset information, asset matching and screening can be performed directly based on the IP address, application name, and number of application system files of the target host;

[0015] If the rough matching stage fails, it means that there are changes in the application assets, and it is necessary to feedback the changes and remind manual inspection of the application version number. If the rough matching stage passes, fine matching will continue.

[0016] As a preferred solution of the industrial control system asset identification and risk warning method of the present invention, the precise matching process includes:

[0017] Generate application system file hash values ​​for each file in the application system folder;

[0018] Fill the application system file hash values ​​of all files into a string array row by row;

[0019] The string arrays are compared using an algorithm based on an embedded model, and during the comparison process, the order of files in the application folder is kept fixed, the sizes of the two string arrays being compared are unique, and each row of the application system file hash value of the tested asset array corresponds to the array hash value of the file in the asset and vulnerability risk information library;

[0020] Mark the collected application system file hash value string array and convert the string array into a matrix for analysis, that is, map each number and letter to a unique identifier, Arabic numerals "0-9" correspond to "0-9", and English letters "az" correspond to "10-35";

[0021] In order to avoid the avalanche effect of the hash algorithm when comparing two data matrices, the data in the first column and the second column of the data matrix are intercepted and compared with the data in the asset and vulnerability risk information library;

[0022] If the data in the first and second columns of the data matrix are different from the data in the asset and vulnerability risk information library, the row of the string array in which the data appears is fed back, the location of the change is located, and the asset change is reported;

[0023] If the data in the first column and the second column of the data matrix are consistent with the data in the asset and vulnerability risk information library, the processed high-dimensional matrix is ​​collected and multiplied by a dimensionality reduction matrix consisting only of 1s and 0s to obtain an N×N dimensional matrix for comparison.

[0024] As a preferred solution of the industrial control system asset identification and risk warning method of the present invention, the method of determining whether the asset information has a vulnerability risk after identifying the application asset version number of the target device includes:

[0025] The scanned assets are matched and identified by combining coarse matching and fine matching. If the match is successful, the asset identification status is recorded. If the match is not successful, there are changes in the application assets, and the changes are fed back and a manual check of the application version number and vulnerability risk information is prompted.

[0026] The version information of each application is different on different industrial control devices. The different application update statuses between devices lead to vulnerability information in the old version of the application. After identifying the application asset version number of the target device, it is determined whether the asset information has vulnerability risks. If the vulnerability risk is found, an early warning is issued and the application is updated;

[0027] When asset identification finds that the version information is outdated, it will remind the system of vulnerability risks and notify the management personnel to update the application. For the updated assets, the system administrator will decide whether to update and overwrite the original assets and vulnerability risk information library. For the newly added types of assets of the target device, the assets and vulnerability risk information library will be updated according to the application name and version number.

[0028] As a preferred solution of the industrial control system asset identification and risk warning method of the present invention, wherein: the asset scanning is performed by remotely logging into the target host through the secure shell protocol, and the asset information of each target industrial control device is actively detected, including:

[0029] Initiate a connection request through the secure shell protocol client to remotely log in to the target host, ensure information transmission security during the connection process, and perform asset detection and collection according to business needs and security policies;

[0030] The collected asset information data is preliminarily classified using the BERT pre-training model, and a sampling method with replacement is used to randomly select a portion of samples from the original training set to construct multiple new training sets, and the original training set is repeatedly sampled multiple times to construct multiple different training sets;

[0031] The original BERT model is trained with each new training set. The same model structure and hyperparameters are used for each new training set, but the training is performed on different training sets. The trained multiple models are integrated to classify the collected asset information data to ensure accurate asset information.

[0032] As a preferred solution of the industrial control system asset identification and risk warning method of the present invention, if the vulnerability risk is found, issuing a warning and performing application update includes:

[0033] Classify the impact level according to the impact of the vulnerability;

[0034] Determine data information of different applications and the impact level when a vulnerability occurs, wherein the data information of different applications includes one or a combination of components and versions, development languages ​​and versions, and database types and versions;

[0035] A machine learning model is established, and the data information of the different applications and the corresponding impact levels are used as input feature sets and output label sets respectively, and the model is trained, fitted and optimized to obtain a system impact prediction model.

[0036] In a second aspect, the present invention provides an industrial control system asset identification and risk warning system, comprising:

[0037] The asset detection module is used to remotely log in to the target host through the secure shell protocol to perform asset scanning and actively detect the asset information of each target industrial control device;

[0038] The asset visualization module is used to pre-establish an asset and vulnerability risk information database based on the key information of the industrial control system, store system assets and vulnerability information data, and classify and partition the assets of each target device;

[0039] The asset matching module is used to match and identify the scanned assets by combining coarse matching and fine matching. The coarse matching mainly roughly screens the asset information by the client's IP address, application name, and the number of application system files. The fine matching uses the embedded model to match the application file hash value to determine the version number of the application.

[0040] The asset tamper-proof module is used to store the relevant information of application assets using hash values. Due to the tamper-proof nature of the hash algorithm, when a certain application file is slightly modified, the asset changes are effectively reflected;

[0041] The monitoring and early warning module is used to identify the application asset version number of the target device and determine whether the asset information has a vulnerability risk. If the vulnerability risk is found, an early warning is issued and the application is updated.

[0042] In a third aspect, the present invention provides a computing device, comprising:

[0043] Memory and processor;

[0044] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method are implemented.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which implement the steps of the method when executed by a processor.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows: in practical applications, the present invention can not only accurately track the status changes of assets, but also provide real-time and reliable risk warnings for industrial control systems, helping system managers make more informed decisions. This highly automated and intelligent asset identification and risk warning system has brought greater convenience and benefits to the industrial control industry, laying a solid foundation for the sustainable development of future industrial control networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0048] Figure 1 This is an overall flow chart of an industrial control system asset identification and risk warning method according to an embodiment of the present invention;

[0049] Figure 2An asset identification flow chart of an industrial control system asset identification and risk warning method according to an embodiment of the present invention;

[0050] Figure 3 A system architecture diagram of an industrial control system asset identification and risk warning method according to an embodiment of the present invention;

[0051] Figure 4 A schematic diagram of system modules of an industrial control system asset identification and risk warning method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0053] Example 1

[0054] Reference Figure 1 to Figure 4 As an embodiment of the present invention, a method for asset identification and risk warning of an industrial control system is provided, which specifically includes the following steps:

[0055] S100: Pre-establish an asset and vulnerability risk information database based on the key information of the industrial control system;

[0056] In the embodiment of the present application, the key information of the industrial control system includes the device IP address, application name and version number, number of application system files, application system file hash value, and application vulnerability information;

[0057] It should be noted that the device IP address, application name and version number, number of application system files, and application system file hash value are used for asset matching to jointly determine the version number of each target industrial control device application; when the application version of each target industrial control device is updated, the vulnerability risks existing in the old version are actively added to the asset and vulnerability risk information library.

[0058] It should be stated that Figure 3 As shown, the system is deployed on an independent host. When deploying the system, ensure that the communication between the system and the target device is normal to achieve comprehensive asset identification and risk early warning protection; establish an asset and vulnerability risk information database in advance. During the establishment of the asset and vulnerability risk information database, record the key information of the industrial control system in detail, including the device IP address, the specific name and version number of the application, the number of files related to the application system and the hash value, and vulnerability information, to provide comprehensive data support for subsequent asset detection and matching.

[0059] S200: Remotely log in to the target host through the secure shell protocol to perform asset scanning and actively detect the asset information of each target industrial control device;

[0060] In the embodiment of the present application, a connection request is initiated through a secure shell protocol client to remotely log in to the target host, and information transmission security is ensured during the connection process, and asset detection and collection are performed according to business requirements and security policies;

[0061] The BERT pre-trained model is used to preliminarily classify the collected asset information data. A sampling method with replacement is used to randomly select a portion of samples from the original training set to construct multiple new training sets. The original training set is sampled multiple times to construct multiple different training sets.

[0062] The original BERT model is trained with each new training set. The same model structure and hyperparameters are used for each new training set, but the training is performed on different training sets. The trained multiple models are integrated to classify the collected asset information data to ensure accurate asset information.

[0063] S300: matching and identifying the scanned assets by combining coarse matching and fine matching;

[0064] In the embodiments of the present application, Figure 2 As shown, the rough matching process includes:

[0065] According to the established asset and vulnerability risk information database, each industrial control device is divided into asset partitions. One target industrial control device corresponds to one asset and vulnerability risk information database table. Different applications on each target industrial control device are distinguished by version name and version number.

[0066] In the rough matching stage, if there is less asset information, asset matching and screening can be performed directly based on the IP address, application name, and number of application system files of the target host;

[0067] If the rough matching stage fails, it means that there are changes in the application assets. It is necessary to feedback the changes and remind manual inspection of the application version number. If the rough matching stage passes, continue with the fine matching.

[0068] Further, such as Figure 2 As shown in the figure, the precise matching process includes:

[0069] Generate application system file hash values ​​for each file in the application system folder;

[0070] Fill the application system file hash values ​​of all files into a string array row by row;

[0071] The string arrays are compared using an algorithm based on an embedded model. During the comparison process, the order of files in the application folder is kept fixed, the sizes of the two string arrays being compared are unique, and the hash value of the application system file in each row of the asset array under test corresponds to the array hash value of the file in the asset and vulnerability risk information library.

[0072] The collected application system file hash value string array is marked and converted into a matrix for analysis, that is, each number and letter is mapped to a unique identifier, Arabic numerals "0-9" corresponds to "0-9", and English letters "az" correspond to "10-35";

[0073] In order to avoid the avalanche effect of the hash algorithm when comparing two data matrices, the data in the first and second columns of the data matrix are intercepted and compared with the data in the asset and vulnerability risk information library;

[0074] If the data in the first and second columns of the data matrix are different from the data in the asset and vulnerability risk information library, the feedback will indicate which row of the string array the data appears in, locate the changed position, and report the asset change.

[0075] If the data in the first and second columns of the data matrix are consistent with the data in the asset and vulnerability risk information library, the processed high-dimensional matrix is ​​collected and multiplied by a dimensionality reduction matrix consisting of only 1s and 0s to obtain an N×N dimensional matrix for comparison.

[0076] S400: After identifying the application asset version number of the target device, determine whether the asset information has a vulnerability risk. If a vulnerability risk is found, issue a warning and perform an application update.

[0077] In the embodiment of the present application, the scanned assets are matched and identified by combining coarse matching and fine matching. If the match is successful, the asset identification is recorded. If the match is not successful, there is a change in the application assets, the change is fed back and a manual check of the application version number and vulnerability risk information is prompted.

[0078] The version information of each application is different on different industrial control devices. The different application update statuses between devices lead to vulnerability information in the old version of the application. After identifying the application asset version number of the target device, it is determined whether the asset information has vulnerability risks. If vulnerability risks are found, an early warning is issued and the application is updated;

[0079] When asset identification finds that the version information is outdated, it will remind the system of vulnerability risks and notify the management personnel to update the application. For the updated assets, the system administrator will decide whether to update and overwrite the original assets and vulnerability risk information library. For the newly added types of assets of the target device, the asset and vulnerability risk information library will be updated according to the application name and version number.

[0080] Furthermore, if a vulnerability risk is found, an early warning will be issued and the application will be updated, including:

[0081] Classify the impact level according to the impact of the vulnerability;

[0082] Determine the data information of different applications and the impact level when vulnerabilities occur, where the data information of different applications includes one or a combination of components and versions, development languages ​​and versions, and database types and versions;

[0083] A machine learning model is established, and the data information of different applications and the corresponding impact levels are used as the input feature set and output label set respectively. The model is trained, fitted and optimized to obtain the system impact prediction model.

[0084] It should be noted that the impact level can include 8 levels from 3 to 10; formulate a strategy for sending security vulnerability warning reports based on the current time and the risk level of the vulnerability;

[0085] For example, if it is currently working hours, a security vulnerability warning report will be sent to the responsible person at any risk level. If it is currently off-duty time, whether to send a warning report will be determined based on the level. For example, if it is lower than level 6, no report will be sent, and the report will be sent when the working hours arrive. If it is higher than or equal to 6, there is no need to pay attention to whether it is currently working hours or off-duty time, and the report will be sent to the responsible person for timely resolution. Based on the above strategy, it is possible to avoid disturbing the responsible person due to the impact of low-risk vulnerabilities during off-duty time. Low-risk vulnerabilities can be handled uniformly during working hours, and high-risk vulnerabilities are promptly notified to the responsible person for processing, avoiding major impacts on the unit's information security.

[0086] As can be seen from the above, in practical applications, the present invention can not only accurately track the status changes of assets, but also provide real-time and reliable risk warnings for industrial control systems, helping system managers make more informed decisions. This highly automated and intelligent asset identification and risk warning system has brought greater convenience and benefits to the industrial control industry, laying a solid foundation for the sustainable development of future industrial control networks.

[0087] The above is a schematic scheme of an industrial control system asset identification and risk warning method of this embodiment. It should be noted that the technical scheme of the industrial control system asset identification and risk warning system and the technical scheme of the industrial control system asset identification and risk warning method described above belong to the same concept. For details not described in detail in the technical scheme of the industrial control system asset identification and risk warning system in this embodiment, please refer to the description of the technical scheme of the industrial control system asset identification and risk warning method described above.

[0088] This embodiment also provides an industrial control system asset identification and risk warning system, such as Figure 4 As shown, specifically including:

[0089] The asset detection module is used to remotely log in to the target host through the secure shell protocol to perform asset scanning and actively detect the asset information of each target industrial control device;

[0090] The asset visualization module is used to pre-establish an asset and vulnerability risk information database based on the key information of the industrial control system, store system assets and vulnerability information data, and classify and partition the assets of each target device;

[0091] The asset matching module is used to match and identify the scanned assets by combining coarse matching and fine matching. The coarse matching mainly roughly screens the asset information by the client's IP address, application name, and the number of application system files. The fine matching uses the embedded model to match the application file hash value to determine the version number of the application.

[0092] The asset tamper-proof module is used to store the relevant information of application assets using hash values. Due to the tamper-proof nature of the hash algorithm, when a certain application file is slightly modified, the asset changes are effectively reflected;

[0093] The monitoring and early warning module is used to identify the application asset version number of the target device and determine whether the asset information has a vulnerability risk. If a vulnerability risk is found, an early warning is issued and the application is updated.

[0094] It should be noted that the present invention is built on the basis of active identification and monitoring to form an advanced asset identification and risk warning system. This system is not only an asset information integration platform, but also an efficient and safe solution. The modules work together to achieve accurate asset identification and risk warning, which can help the industrial control system better manage and monitor the dynamic changes of assets and warn of possible risks.

[0095] This embodiment also provides a computing device, including:

[0096] Memory and processor;

[0097] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method proposed in the above embodiment.

[0098] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method proposed in the above embodiment is implemented.

[0099] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0100] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0101] Example 2

[0102] Based on the previous embodiment, this embodiment provides an application example of an industrial control system asset identification and risk warning method and system to verify and illustrate the technical effects adopted in this method.

[0103] This embodiment firstly establishes an asset and vulnerability risk information database in advance based on the key information of the industrial control system, then remotely logs in to the target host through the secure shell protocol to perform asset scanning, and actively detects the asset information of each target industrial control device; then uses a combination of coarse matching and fine matching to match and identify the scanned assets;

[0104] Rough matching stage: Since the asset information in this part is concise and clear, the IP address, application name, and number of application system files of the target device are directly converted into a string, which is compared with the corresponding information in the asset and vulnerability risk information library to output the matching result;

[0105] Precise matching stage: Determine the version number of the application system based on the hash value of the application system file:

[0106] Since the application system folder contains multiple files, a hash value is generated for each file and stored in a string array row by row. Assuming that there are three files in an application system folder, the hash values ​​of these three files in the asset library are stored as follows:

[0107] Hash value 1-1: dbe2c84a709ff06af03bc4db8319f5db,

[0108] Hash value 2-1: bb67a4d2308b34c500eed745e4836756,

[0109] Hash value 3-1: 099fb9c3c39dd6580423a2438d0a5173,

[0110] Generates a string array

[0111] In the actual asset identification process, hash values ​​are generated for these three files in the application system folder:

[0112] Hash value 1-2: 67a4d2308b34c500eed745e483675612,

[0113] Hash value 2-2: 4567a4d2308b349900eed745acf36756,

[0114] Hash value 3-2: a4d2308b349900eed745acf367565448,

[0115] Generates a string array

[0116] Note: The sizes of the two string arrays to be compared are unique (the length of the hash value is fixed. After the rough match is passed, it can be determined that the number of files in the application system folder is the same, the application system has not been significantly modified, and only one file may have been modified). This ensures that the order of files in the application folder is fixed, and that when identifying assets, each row of the hash value of the tested asset array corresponds to the array hash value of the file in the asset and vulnerability risk information library;

[0117] Use the embedding model to perform hash comparison to check whether the two string arrays are consistent; "Embedding" literally means embedded or embedded layer; mathematically speaking, it is injective and isomorphic. Suppose there are only 10 characters in the database, then we can use 0-9 to represent them all. For example, these ten characters are "Hello, may I ask whose child he is?" and they correspond to "0-9" respectively, as follows:

[0118]

[0119] So no matter how this sentence changes, such as "Hello, whose child is he?", "Whose child is he?", "Excuse me, whose child is he?", "Excuse me, whose child is he?", it can be expressed using ten numbers:

[0120]

[0121] Since the hash value is represented by only ten numbers "0-9" and 26 English letters "az", any hash value can be marked by 36 numbers. The collected string array can be represented by a pure digital matrix, that is, the collected string array can be vectorized.

[0122] Tokenize the collected asset hash value string arrays, that is, map each number and letter to a unique identifier, that is, Arabic numerals "0-9" correspond to "0-9", and English letters "az" correspond to "10-35". Perform tokenization preprocessing on the collected string arrays A1 and A2. A1 and A2 are arrays of 3 rows and 32 columns, which can be transformed into two data matrices B1 and B2. The dimensions of B1 and B2 are 3×32.

[0123] Due to the avalanche effect of the hash algorithm, when a file is slightly modified, a huge difference will occur. When comparing two data matrices, in order to reduce the complexity of the algorithm, the data in the first and second columns of the matrix are intercepted for comparison. If there is a difference, the feedback is given on which row of the array the difference appears, the location of the change is located, and the asset change is reported;

[0124] If the two matrices pass the comparison in the above steps, the two matrices are simplified and compared by using dimensionality reduction. For example, two N×32-dimensional matrices are respectively multiplied by a 32×N-dimensional dimensionality reduction matrix consisting of only 1s and 0s to obtain two N×N-dimensional matrices for comparison to confirm whether they are the same.

[0125] Finally, after identifying the application asset version number of the target device, it is determined whether the asset information has a vulnerability risk. If a vulnerability risk is found, an early warning is issued and the application is updated.

[0126] As can be seen from the above, in practical applications, the present invention can not only accurately track the status changes of assets, but also provide real-time and reliable risk warnings for industrial control systems, helping system managers make more informed decisions. This highly automated and intelligent asset identification and risk warning system has brought greater convenience and benefits to the industrial control industry, laying a solid foundation for the sustainable development of future industrial control networks.

[0127] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for asset identification and risk warning of industrial control systems, It is characterized in that include: Pre-establish an asset and vulnerability risk information database based on the key information of the industrial control system; Remotely log in to the target host through the secure shell protocol to scan assets and actively detect the asset information of each target industrial control equipment; Use a combination of coarse matching and fine matching to match and identify the scanned assets; After identifying the application asset version number of the target device, determine whether the asset information has a vulnerability risk. If the vulnerability risk is found, issue an early warning and perform an application update.

2. The industrial control system asset identification and risk warning method according to claim 1, It is characterized in that The establishment of the asset and vulnerability risk information database includes: Pre-establish an asset and vulnerability risk information library based on key information of the industrial control system, where the key information of the industrial control system includes device IP address, application name and version number, number of application system files, application system file hash value, and application vulnerability information; The device IP address, application name and version number, application system file quantity, and application system file hash value are used for asset matching to jointly determine the version number of each target industrial control device application; When the application version of each target industrial control device is updated, the vulnerability risks existing in the old version are actively added to the asset and vulnerability risk information library.

3. The industrial control system asset identification and risk warning method as claimed in claim 2, It is characterized in that The rough matching process includes: According to the established asset and vulnerability risk information database, each industrial control device is divided into asset partitions. One target industrial control device corresponds to one asset and vulnerability risk information database table. Different applications on each target industrial control device are distinguished by version name and version number. In the rough matching stage, if there is less asset information, asset matching and screening can be performed directly based on the IP address, application name, and number of application system files of the target host; If the rough matching stage fails, it means that there are changes in the application assets, and it is necessary to feedback the changes and remind manual inspection of the application version number. If the rough matching stage passes, fine matching will continue.

4. The industrial control system asset identification and risk warning method according to claim 3, It is characterized in that The precise matching process includes: Generate application system file hash values ​​for each file in the application system folder; Fill the application system file hash values ​​of all files into a string array row by row; The string arrays are compared using an algorithm based on an embedded model, and during the comparison process, the order of files in the application folder is kept fixed, the sizes of the two string arrays being compared are unique, and each row of the application system file hash value of the tested asset array corresponds to the array hash value of the file in the asset and vulnerability risk information library; Mark the collected application system file hash value string array and convert the string array into a matrix for analysis, that is, map each number and letter to a unique identifier, Arabic numerals "0-9" correspond to "0-9", and English letters "az" correspond to "10-35"; In order to avoid the avalanche effect of the hash algorithm when comparing two data matrices, the data in the first column and the second column of the data matrix are intercepted and compared with the data in the asset and vulnerability risk information library; If the data in the first and second columns of the data matrix are different from the data in the asset and vulnerability risk information library, the row of the string array in which the data appears is fed back, the location of the change is located, and the asset change is reported; If the data in the first column and the second column of the data matrix are consistent with the data in the asset and vulnerability risk information library, the processed high-dimensional matrix is ​​collected and multiplied by a dimensionality reduction matrix consisting only of 1s and 0s to obtain an N×N dimensional matrix for comparison.

5. The industrial control system asset identification and risk warning method according to claim 4, It is characterized in that The step of identifying the application asset version number of the target device and determining whether the asset information has a vulnerability risk includes: The scanned assets are matched and identified by combining coarse matching and fine matching. If the match is successful, the asset identification status is recorded. If the match is not successful, there are changes in the application assets, and the changes are fed back and a manual check of the application version number and vulnerability risk information is prompted. The version information of each application is different on different industrial control devices. The different application update statuses between devices lead to vulnerability information in the old version of the application. After identifying the application asset version number of the target device, it is determined whether the asset information has vulnerability risks. If the vulnerability risk is found, an early warning is issued and the application is updated; When asset identification finds that the version information is outdated, it will remind the system of vulnerability risks and notify the management personnel to update the application. For the updated assets, the system administrator will decide whether to update and overwrite the original assets and vulnerability risk information library. For the newly added types of assets of the target device, the assets and vulnerability risk information library will be updated according to the application name and version number.

6. The industrial control system asset identification and risk warning method according to claim 1, It is characterized in that The asset scanning by remotely logging into the target host through the secure shell protocol and actively detecting the asset information of each target industrial control device includes: Initiate a connection request through the secure shell protocol client to remotely log in to the target host, ensure information transmission security during the connection process, and perform asset detection and collection according to business needs and security policies; The collected asset information data is preliminarily classified using the BERT pre-training model, and a sampling method with replacement is used to randomly select a portion of samples from the original training set to construct multiple new training sets, and the original training set is repeatedly sampled multiple times to construct multiple different training sets; The original BERT model is trained with each new training set. The same model structure and hyperparameters are used for each new training set, but the training is performed on different training sets. The trained multiple models are integrated to classify the collected asset information data to ensure accurate asset information.

7. The industrial control system asset identification and risk warning method according to claim 1, It is characterized in that If the vulnerability risk is found, issuing a warning and performing application updates include: Classify the impact level according to the impact of the vulnerability; Determine data information of different applications and the impact level when a vulnerability occurs, wherein the data information of different applications includes one or a combination of components and versions, development languages ​​and versions, and database types and versions; A machine learning model is established, and the data information of the different applications and the corresponding impact levels are used as input feature sets and output label sets respectively, and the model is trained, fitted and optimized to obtain a system impact prediction model.

8. A system using the industrial control system asset identification and risk warning method according to any one of claims 1 to 7, It is characterized in that include: The asset detection module is used to remotely log in to the target host through the secure shell protocol to perform asset scanning and actively detect the asset information of each target industrial control device; The asset visualization module is used to pre-establish an asset and vulnerability risk information database based on the key information of the industrial control system, store system assets and vulnerability information data, and classify and partition the assets of each target device; The asset matching module is used to match and identify the scanned assets by combining coarse matching and fine matching. The coarse matching mainly roughly screens the asset information by the client's IP address, application name, and the number of application system files. The fine matching uses the embedded model to match the application file hash value to determine the version number of the application. The asset tamper-proof module is used to store the relevant information of application assets using hash values. Due to the tamper-proof nature of the hash algorithm, when a certain application file is slightly modified, the asset changes are effectively reflected; The monitoring and early warning module is used to identify the application asset version number of the target device and determine whether the asset information has a vulnerability risk. If the vulnerability risk is found, an early warning is issued and the application is updated.

9. An electronic device, include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having computer program instructions stored thereon, wherein the computer-executable instructions, when executed by a processor, implement the steps of the method according to any one of claims 1 to 7.