Network security situation inversion method and device
By building the initial system model and using historical prior knowledge to correct parameters and simulate and deduce the target system model, the problem of incomplete data information in network security situation awareness is solved, the comprehensiveness and reliability of data is improved, and the network is improved The effectiveness of security monitoring and the stability and security of information systems.
Patent Information
- Application Number
- CN202310532624.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-11
- Publication Date
- 2024-11-12
AI Technical Summary
Existing network security situation awareness technology cannot form effective security situation data when data information is incomplete or missing, resulting in the inability to ensure the comprehensiveness and reliability of the data, which in turn affects the effectiveness of network monitoring.
By building an initial system model, using the prior knowledge of historical network security situations to perform parameter correction and simulation environment simulation and deduction, the target system model is optimized and adjusted to improve the comprehensiveness and reliability of the data.
It effectively improves the comprehensiveness and reliability of network security situation data, improves the effectiveness of network security monitoring and timely maintenance, and improves the operation stability and security of information systems.
Smart Images

Figure CN118944903A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of information system network security, and in particular to a network security situation inversion method and device. Background Art
[0002] The network security situation awareness of information systems can obtain a macro and comprehensive understanding of the network security situation of information systems by collecting comprehensive and comprehensive security elements in the network environment and integrating data. It can also predict the network security situation (i.e. trend) of information systems, which is an effective means to ensure network security. Therefore, it is necessary to obtain data that can represent the network security situation of information systems.
[0003] At present, the data that can represent the network security situation of information systems is mainly obtained by actively detecting or passively collecting system-related parameter information, and then associating and fusing the parameter information to form data that reflects the network security situation of information systems. Among them, the active detection method mainly uses a variety of high-speed network scanning technologies, such as host survival detection, port scanning, and service identification, and also includes the use of network crawlers and other methods to obtain relevant information. The passive collection method is mainly through the image capture of network traffic, the collection of information such as logs, and the collection of information through the honeynet composed of honeypots.
[0004] However, the existing network security situation awareness technology performs correlation analysis and fusion from data obtained actively and passively. If the data information is incomplete or missing, an effective security situation cannot be formed for this part of the target; therefore, the comprehensiveness and reliability of the data finally obtained to represent the network security situation of the information system cannot be guaranteed, and further, the effectiveness of network monitoring of the information system based on the data used to represent the network security situation of the information system cannot be guaranteed. Summary of the invention
[0005] In view of this, the embodiments of the present application provide a network security situation inversion method and device to eliminate or improve one or more defects existing in the prior art.
[0006] One aspect of the present application provides a network security situation inversion method, comprising:
[0007] Based on the prior knowledge of historical network security situation, an initial system model is constructed to reflect the network security situation of the target information system;
[0008] Performing target reconnaissance on the target information system, and modifying parameters of the initial system model according to corresponding target reconnaissance result data to obtain a corresponding target system model;
[0009] Construct a simulation environment for the target system model, perform state simulation and deduction on the target system model in the simulation environment, and optimize and adjust the target system model according to the corresponding simulation and deduction results.
[0010] In some embodiments of the present application, the prior knowledge includes:
[0011] A situation database for storing historical network security situation information, expert knowledge for reflecting historical network security situation, and historical system models corresponding to each type of historical information system.
[0012] In some embodiments of the present application, the construction of an initial system model for reflecting the network security situation of the target information system based on the prior knowledge of the historical network security situation includes:
[0013] Get the type of target information system;
[0014] It is determined whether the historical information systems of various types contain a historical information system of the same type as the target information system. If so, the historical system model corresponding to the historical information system is used as the initial system model corresponding to the target information system.
[0015] In some embodiments of the present application, it also includes:
[0016] If the historical information systems of various types are different from the target information system type, knowledge discovery processing is performed on the situation database based on a preset artificial intelligence algorithm to obtain decision rule data for constructing an initial system model corresponding to the target information system, and / or decision rule data for constructing an initial system model corresponding to the target information system is constructed based on the expert knowledge;
[0017] An initial system model corresponding to the target information system is constructed based on the decision rule data.
[0018] In some embodiments of the present application, the target information system is reconnaissance-performed, and the initial system model is parameter-corrected according to the corresponding target reconnaissance result data to obtain the corresponding target system model, including:
[0019] Conducting target reconnaissance on the target information system based on a preset target reconnaissance method to obtain various types of parameter information used to reflect the network security situation of the target information system, wherein the various types of parameter information used to reflect the network security situation of the target information system include: the IP address, host information, network information, user information, information about the organization to which the user belongs, business relationship, and network security vulnerability information of the target information system;
[0020] The initial system model is modified according to the parameter information to obtain a corresponding target system model.
[0021] In some embodiments of the present application, the construction of a simulation environment for the target system model, performing state simulation and deduction on the target system model in the simulation environment, and optimizing and adjusting the target system model according to the corresponding simulation and deduction results include:
[0022] Simulating the target system model to form a simulation environment with an interactive interface;
[0023] receiving simulated access point information sent by a user from the interactive interface, and setting different access points for the target system model in the simulation environment according to the simulated access point information, so that the user can perform state simulation deduction on the target system model in the simulation environment according to each of the access points to obtain different system states corresponding to the target system model;
[0024] Performing state evaluation on each of the system states respectively, and selecting one of the system states as the optimal system state based on the corresponding state evaluation result, the prior knowledge and the target detection result data, and generating a corresponding adjustment plan based on the optimal system state;
[0025] The target system model is optimized and adjusted based on the adjustment scheme.
[0026] In some embodiments of the present application, the target system model is used to represent the IP, host information, network information, user information, user organization information, business relationships and network security vulnerability information of the target information system.
[0027] Another aspect of the present application provides a network security situation inversion device, comprising:
[0028] A model building module, used to build an initial system model for reflecting the network security situation of the target information system based on the prior knowledge of the historical network security situation;
[0029] A parameter correction module is used to perform target reconnaissance on the target information system and perform parameter correction on the initial system model according to the corresponding target reconnaissance result data to obtain a corresponding target system model;
[0030] The model inversion module is used to construct a simulation environment for the target system model, and perform state simulation and deduction on the target system model in the simulation environment, and optimize and adjust the target system model according to the corresponding simulation and deduction results.
[0031] The third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the network security situation inversion method when executing the computer program.
[0032] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the network security situation inversion method when executed by a processor.
[0033] The network security situation inversion method provided in the present application constructs an initial system model for reflecting the network security situation of a target information system based on prior knowledge of historical network security situations; performs target reconnaissance on the target information system, and performs parameter correction on the initial system model based on corresponding target reconnaissance result data to obtain a corresponding target system model; constructs a simulation environment for the target system model, and performs state simulation and deduction on the target system model in the simulation environment, and optimizes and adjusts the target system model based on the corresponding simulation and deduction results, which can effectively improve the comprehensiveness and reliability of data in the target system model used to represent the network security situation of the information system, and further improve the effectiveness of network security monitoring of the target information system based on the target system model and the timeliness of maintenance, so as to effectively improve the operational stability and security of the target information system.
[0034] Additional advantages, purposes, and features of the present application will be partially described in the following description, and will become partially apparent to those skilled in the art after studying the following, or may be learned from the practice of the present application. The purposes and other advantages of the present application can be achieved and obtained by the structures specifically pointed out in the specification and the drawings.
[0035] Those skilled in the art will understand that the purposes and advantages that can be achieved by the present application are not limited to the above specific description, and the above and other purposes that can be achieved by the present application will be more clearly understood based on the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The drawings described herein are used to provide a further understanding of the present application, constitute a part of the present application, and do not constitute a limitation of the present application. The components in the drawings are not drawn to scale, but are only for the purpose of illustrating the principles of the present application. In order to facilitate the illustration and description of some parts of the present application, the corresponding parts in the drawings may be enlarged, that is, they may become larger relative to other components in the exemplary device actually manufactured according to the present application. In the drawings:
[0037] Figure 1 This is a schematic diagram of a first flow chart of a network security situation inversion method in an embodiment of the present application.
[0038] Figure 2 This is a second flow chart of the network security situation inversion method in one embodiment of the present application.
[0039] Figure 3 Schematic diagram of the structure of a network security situation inversion device in one embodiment of the present application.
[0040] Figure 4 A schematic diagram of the mechanism of the network security situation inversion method provided in the application example of this application. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the implementation modes and the accompanying drawings. Here, the illustrative implementation modes and descriptions of the present application are used to explain the present application, but are not intended to limit the present application.
[0042] It should also be noted here that in order to avoid obscuring the present application due to unnecessary details, only the structures and / or processing steps closely related to the scheme according to the present application are shown in the accompanying drawings, while other details that are not very relevant to the present application are omitted.
[0043] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.
[0044] It should also be noted that, unless otherwise specified, the term “connection” herein may refer not only to a direct connection but also to an indirect connection involving an intermediate.
[0045] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals represent the same or similar components, or the same or similar steps.
[0046] Inversion means: given a mathematical abstract form, AZ = u, where Z∈F, u∈U, and F and U are function sets or spaces that satisfy certain conditions. In mathematics, A can be called an operator, and in physics, A can be called a model. The problem of inversion is to find Z when A and u are known.
[0047] From the perspective of natural science and engineering technology, inversion method is a method that is widely studied and applied in differential equations and geophysics; from the perspective of logic and psychology, it is a sub-method of the two basic reasoning methods of human beings: deductive reasoning and inductive reasoning.
[0048] In the field of geophysics, for an observable physical system S, if a set of model parameters that fully describe S can be defined, and these parameters are not all directly measurable, then some observable parameters can be computationally specified, hoping that their actual values depend on the model parameters. Solving the forward problem is to predict the observable parameter values for given model parameter values; solving the inverse problem is to infer the values of the model parameters based on given observable parameter values.
[0049] In the fields of automation, electronics and electronic engineering, research on inversion problems includes system identification, pattern recognition, data fusion, parameter estimation, radar imaging, medical imaging, remote sensing and telemetry, spectrum estimation, radio direction finding and signal intelligence extraction, all of which use the observation values of the corresponding physical system to infer the corresponding parameter values.
[0050] In one or more embodiments of the present application, a honeypot is a software application system used as an intrusion bait to lure hackers to attack. After the attacker invades, through monitoring and analysis, it is possible to know how he invaded and keep abreast of the latest attacks and vulnerabilities launched against the organization's servers. When multiple honeypots are connected together by a network, a large network is simulated, and some of the hosts are used to attract hackers to invade. By monitoring and observing the invasion process, on the one hand, the source of the intruder is investigated, and on the other hand, the effectiveness of the security measures used for protection is examined. This simulated network composed of multiple honeypots is called a honeynet.
[0051] In one or more embodiments of the present application, the network security situation inversion technology provided by the present application is mainly used for the accurate characterization of the security situation of key target information systems. In the target reconnaissance phase (Reconnaissance) of the target information system, due to limited conditions, the target-related information obtained by the reconnaissance is limited. On this basis, the inversion technology is used to first establish a system model of the target information system based on previous knowledge and experience, and then through re-detection, calculation or simulation deduction, etc., the system model is gradually revised and refined, so that the system model can truly and accurately characterize the target.
[0052] The details are described in detail through the following examples.
[0053] Based on this, the embodiment of the present application provides a network security situation inversion method that can be implemented by a network security situation inversion device, see Figure 1 , the network security situation inversion method specifically includes the following contents:
[0054] Step 100: Based on the prior knowledge of historical network security situations, an initial system model is constructed to reflect the network security situation of the target information system.
[0055] In one or more embodiments of the present application, the prior knowledge of the historical network security situation is derived from the relevant information that has been acquired about the network security situation of the target information system, knowledge discovery in the existing situation database, historical system models and parameters of the same type of system, expert knowledge, etc.
[0056] It can be understood that the initial system model used to reflect the network security situation of the target information system refers to the structure and process description of the target information system, which contains parameter information used to reflect the network security situation of the target information system.
[0057] In step 100, the specific method of constructing an initial system model for reflecting the network security situation of the target information system based on prior knowledge of historical network security situation can refer to determining parameter information related to the network security trend of the target information system through prior knowledge, and determining core parameter information from these parameter information according to user instructions, and constructing the initial system model of the target information system based on these core parameter information.
[0058] Step 200: scouting the target information system, and modifying the parameters of the initial system model according to the corresponding target scouting result data to obtain a corresponding target system model.
[0059] It can be understood that the target system model can be used to represent the IP, host information, network information, user information, user organization information, business relationships and network security vulnerability information of the target information system.
[0060] In step 200, the target reconnaissance of the target information system may refer to monitoring and collecting information related to the actual network security trend of the target information system within a preset time period.
[0061] Target reconnaissance technology is to obtain the IP, host information, network information, user / personnel and their organizational information, business relationships and vulnerability information of the target information system through the above various technologies and methods.
[0062] Step 300: construct a simulation environment for the target system model, perform state simulation on the target system model in the simulation environment, and optimize and adjust the target system model according to the corresponding simulation results.
[0063] After obtaining the optimized and adjusted target system model, the target system model can be used to monitor the network security trends of various parameters of the target information system respectively, and when it is determined that the increase or decrease in the value of any parameter exceeds a preset threshold within a preset period of time, a network security warning information for the parameter is issued, so that the operation and maintenance personnel can perform maintenance and risk elimination operations on the target information system in a timely manner according to the warning information.
[0064] From the above description, it can be seen that the network security situation inversion method provided in the embodiment of the present application can effectively improve the comprehensiveness and reliability of the data in the target system model used to represent the network security situation of the information system, and thus can improve the effectiveness of network security monitoring of the target information system based on the target system model and the timeliness of maintenance, so as to effectively improve the operational stability and security of the target information system.
[0065] In order to further improve the reliability and effectiveness of the setting of the initial system model, in a network security situation inversion method provided in an embodiment of the present application, the prior knowledge of the network security situation inversion method specifically includes the following contents:
[0066] A situation database for storing historical network security situation information, expert knowledge for reflecting historical network security situation, and historical system models corresponding to each type of historical information system.
[0067] It can be understood that the historical network security situation information refers to information related to the historical network security situation of the target information system, and may also include information related to the historical network security situation of other information systems, and may also include guidance information related to the general historical network security situation that does not specify a specific type of system.
[0068] The expert knowledge used to reflect the historical network security situation is the expert knowledge data received in advance from the user last time and stored in a local or third-party database for easy retrieval.
[0069] In order to further improve the reliability and effectiveness of the initial system model construction, in a network security situation inversion method provided in an embodiment of the present application, see Figure 2 , step 100 of the network security situation inversion method specifically includes the following contents:
[0070] Step 110: Obtain the type of the target information system.
[0071] In step 110, the type of the target information system uploaded by the user may be received, or the type corresponding to the unique identifier of the target information system may be found from a pre-stored type comparison table.
[0072] Step 120: Determine whether the historical information systems of each type contain a historical information system of the same type as the target information system. If so, execute step 130; if not, in order to further improve the reliability and effectiveness of the initial system model construction, execute steps 140 and 150 in sequence;
[0073] Step 130: Using the historical system model corresponding to the historical information system as the initial system model corresponding to the target information system.
[0074] Specifically, a model is built for a target that has been reconnaissanced and verified in an actual combat environment. The model's level of detail and accuracy has been verified and can be used as a prediction model for targets of the same type to be reconnaissanced. For example, a detailed model is built for a certain industry business system hosted on a public cloud, including network topology, software composition, host information, network protocol, vulnerability information, business relationships, user organizations and other information. When the target to be reconnaissance is confirmed to belong to the industry business system, this existing model can be used to build a prediction model for the target to be reconnaissance and be modified according to the detection and calculation results.
[0075] Step 140: If the historical information systems of various types are different from the target information system type, knowledge discovery processing is performed on the situation database based on a preset artificial intelligence algorithm to obtain decision rule data for constructing an initial system model corresponding to the target information system, and / or, decision rule data for constructing an initial system model corresponding to the target information system is constructed based on the expert knowledge;
[0076] Specifically, artificial intelligence algorithms such as rough sets and cluster analysis can be used to perform knowledge discovery from the situation database and obtain decision rules in the form of "Va∧Vb→U", that is, if the target has attributes a and b, it can be determined that the target belongs to the known set U. It is also possible to establish reasoning rules and decision rules based on expert knowledge and experience, match appropriate rules for the target to be detected, and perform modeling and reasoning.
[0077] Step 150: constructing an initial system model corresponding to the target information system based on the decision rule data.
[0078] In order to further improve the reliability and effectiveness of parameter correction of the initial system model, in a network security situation inversion method provided in an embodiment of the present application, see Figure 2 , step 200 of the network security situation inversion method specifically includes the following contents:
[0079] Step 210: Conduct target reconnaissance on the target information system based on a preset target reconnaissance method to obtain various types of parameter information used to reflect the network security situation of the target information system, wherein the various types of parameter information used to reflect the network security situation of the target information system include: the IP of the target information system, host information, network information, user information, user organization information, business relationship and network security vulnerability information.
[0080] It is understandable that the preset target reconnaissance method can be implemented using the MITRE ATT&CK tool.
[0081] Step 220: modify the parameters of the initial system model according to the parameter information to obtain a corresponding target system model.
[0082] In order to further improve the reliability and effectiveness of optimizing and adjusting the target system model, in a network security situation inversion method provided in an embodiment of the present application, see Figure 2 , step 300 of the network security situation inversion method specifically includes the following contents:
[0083] Step 310: simulating the target system model to form a simulation environment with an interactive interface;
[0084] Step 320: receiving the simulated access point information sent by the user from the interactive interface, and setting different access points for the target system model in the simulation environment according to the simulated access point information, so that the user can perform state simulation deduction on the target system model in the simulation environment according to each of the access points to obtain different system states corresponding to the target system model;
[0085] Step 330: performing state evaluation on each of the system states respectively, and selecting one of the system states as the optimal system state based on the corresponding state evaluation result, the prior knowledge and the target detection result data, and generating a corresponding adjustment plan based on the optimal system state;
[0086] Step 340: Optimize and adjust the target system model based on the adjustment scheme.
[0087] Specifically, the simulation system and environment can provide an interactive interface, and users can simulate access points, perform routing access, and detect information. According to user needs, they can change simulation system parameters and connection relationships, and find the most reasonable simulation system state through detection and evaluation from different angles, thereby determining the most reasonable target model. By setting weights in advance and in a scientific manner, the evaluation algorithm can be used to evaluate the different states of the simulation system that appear during the deduction process, and matching calculations can be performed in combination with actual reconnaissance results and prior knowledge, so as to select the most reasonable simulation system state, generate an adjustment plan for the target model, and optimize the current target model.
[0088] From the software level, the present application also provides a network security situation inversion device for executing all or part of the network security situation inversion method, see Figure 3 The network security situation inversion device specifically includes the following contents:
[0089] The model building module 10 is used to build an initial system model for reflecting the network security situation of the target information system based on the prior knowledge of the historical network security situation.
[0090] The parameter correction module 20 is used to perform target detection on the target information system and perform parameter correction on the initial system model according to the corresponding target detection result data to obtain the corresponding target system model.
[0091] The model inversion module 30 is used to construct a simulation environment for the target system model, and perform state simulation and deduction on the target system model in the simulation environment, and optimize and adjust the target system model according to the corresponding simulation and deduction results.
[0092] The embodiment of the network security situation inversion device provided in the present application can be specifically used to execute the processing flow of the embodiment of the network security situation inversion method in the above-mentioned embodiment. Its functions will not be repeated here, and reference can be made to the detailed description of the embodiment of the above-mentioned network security situation inversion method.
[0093] The part of the network security situation inversion device that performs network security situation inversion can be executed in the server or completed in the client device. It can be selected specifically according to the processing capability of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor for specific processing of network security situation inversion.
[0094] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.
[0095] The server and the client device may communicate with each other using any suitable network protocol, including network protocols that have not yet been developed on the date of filing this application. The network protocols may include, for example, TCP / IP, UDP / IP, HTTP, HTTPS, etc. Of course, the network protocols may also include, for example, RPC (Remote Procedure Call Protocol) and REST (Representational State Transfer) protocols used on top of the above protocols.
[0096] From the above description, it can be seen that the network security situation inversion device provided in the embodiment of the present application can effectively improve the comprehensiveness and reliability of the data in the target system model used to represent the network security situation of the information system, and thus can improve the effectiveness of network security monitoring of the target information system based on the target system model and the timeliness of maintenance, so as to effectively improve the operational stability and security of the target information system.
[0097] In order to further illustrate the present scheme, the present application also provides a specific application example of a network security situation inversion method. In view of the problems of network security situation awareness technology, such as the poor comprehensiveness and reliability of data collection, the application example of the present application proposes a security situation inversion technology. In view of the problems of difficulty in direct detection and missing information in the target detection process, based on the inversion technology method, using the regularity knowledge and expert knowledge in historical data, an observation model (i.e., the aforementioned initial system model) is first established for the detection target (i.e., the target information system), and reasoning and deduction are performed. The measurable parameters in the initial system model are detected and measured, and finally all model parameters are calculated, thereby obtaining a target system model formed by relatively complete target information. See. Figure 4 The network security situation inversion method implemented by the network security situation inversion method device specifically includes the following contents:
[0098] (I) Basic principles
[0099] Network security situation inversion is mainly used for the accurate characterization of key targets. In the target reconnaissance stage (Reconnaissance), due to limited conditions, the target-related information obtained by the initial reconnaissance is limited. On this basis, the inversion technology is used to first establish a model of the target based on previous knowledge and experience, and then through re-detection, calculation or simulation deduction, etc., the model is gradually revised and refined, so that the model can truly and accurately characterize the target and obtain more complete target information.
[0100] (II) Main Process
[0101] For the key targets to be studied, a model is established based on prior knowledge. Prior knowledge comes from the relevant information about the network security situation of the target information system that has been obtained, knowledge discovery in the existing situation database, models and parameters of similar targets, expert knowledge, etc. Then, based on continuous reconnaissance detection, simulation calculation, and deduction technology, the model parameters are corrected so that the model can accurately portray the key targets. The specific instructions are as follows:
[0102] 1. Target reconnaissance
[0103] MITRE ATT&CK is a globally accessible knowledge base of adversary tactics and techniques based on real-world observations. The reconnaissance tactics defined by ATT&CK include 10 techniques, which use active scanning, public database collection and other techniques to collect information such as target networks, hosts, identities, organizations, websites, etc. It is understandable that the embodiments of this application may also use other information reconnaissance technical means and tools, but they are not limited to this.
[0104] 2. Target information
[0105] Target reconnaissance technology is to obtain the target information system's IP, host information, network information, user / personnel and organizational information, business relationships and vulnerability information through the above various technologies and channels. The comprehensiveness and accuracy of reconnaissance to obtain this information is strongly related to the information security measures taken by the target. Generally, it may be necessary to use a combination of multiple techniques and tactics and conduct repeated reconnaissance and detection to obtain effective information.
[0106] In the reconnaissance phase, it is generally difficult to obtain information about key targets that can be effectively used, and continuous detection, calculation, deduction and verification are required. Cyberspace inversion is to use prior knowledge and simulation, deduction, calculation and evaluation technologies to promote the effectiveness and accuracy of target reconnaissance.
[0107] 3. Prior Knowledge
[0108] In order to improve the information about the target, we can use prior knowledge and artificial intelligence technology to deduce and analogize on the basis of known reconnaissance intelligence, establish an information model about the target, predict and infer other unknown key information about the target, and then verify or correct it through simulation, computational evaluation, reconnaissance and detection.
[0109] Prior knowledge mainly comes from existing situation databases and expert knowledge, as well as similar target models of related targets established in the early stage.
[0110] A probability model that can be derived statistically. By performing statistical analysis on the data in the situation database, it is possible to derive a decision rule such as "95% of hosts in the XX region are of the YY brand."
[0111] Models can also be obtained through knowledge discovery. Using artificial intelligence algorithms such as rough sets and cluster analysis, knowledge is discovered from the situation database to obtain decision rules in the form of "Va∧Vb→U", that is, if the target has attributes a and b, it can be determined that the target belongs to the known set U.
[0112] (1) Situation Database
[0113] In order to evaluate the current security situation of the entire network and predict the development of the security situation, it is necessary to continuously collect basic network information, host information, security information, social data information, etc. of the entire network, and connect to threat intelligence, internal industry information, etc., to conduct correlation analysis, discover security risks, evaluate security status and development trends.
[0114] The situation database collects and stores a huge amount of current and historical data related to various types of targets in the entire network. It is necessary to use artificial intelligence algorithms to conduct knowledge discovery and form decision-making rules to provide model and parameter predictions for the inversion of key targets to be detected.
[0115] (2) Expert knowledge
[0116] Based on expert knowledge and experience, inference rules and decision rules are established to match appropriate rules for the targets to be detected, and modeling and reasoning are performed.
[0117] (3) Models with existing goals
[0118] Models are built for targets that have been reconnaissanced and verified in actual combat environments. The model's level of detail and accuracy have been verified and can be used as a prediction model for targets of the same type to be reconnaissanced. For example, a detailed model is built for a business system of a certain industry hosted on a public cloud, including network topology, software composition, host information, network protocol, vulnerability information, business relationships, user organizations, and other information. When the target to be reconnaissance is confirmed to belong to the business system of the industry, this existing model can be used to build a prediction model for the target to be reconnaissance, and it can be modified according to the detection and calculation results.
[0119] 4. Target Model
[0120] The target model (i.e., target system model) is a description of the target structure and process, and a description and definition of attributes, values, and interaction relationships. For an information device, the model consists of IP address (range), online status, host information, network information, organization information, user information, business information, vulnerability information, etc.
[0121] 5. Simulation evaluation
[0122] (1) Target model simulation
[0123] Target model simulation is to build a simulation environment based on the initially determined target model information. According to the target model content, the host, network, business, organization information, user information and vulnerabilities can be simulated, and interactive responses can be made to common detection methods.
[0124] The simulation environment can be automatically generated based on the model, and the quantity, type, connection relationship and other parameters can also be changed with expert intervention.
[0125] (2) Simulation and deduction
[0126] The simulation system and environment can provide an interactive interface. Users can simulate access points, perform routing access, and detect information. According to user needs, they can change simulation system parameters, connection relationships, etc., and find the most reasonable simulation system state through detection and evaluation from different angles, thereby determining the most reasonable target model.
[0127] (3) Calculation evaluation
[0128] By setting weights scientifically and using evaluation algorithms to evaluate the different states of the simulation system that appear during the simulation process, matching calculations are performed based on actual reconnaissance results and prior knowledge, the most reasonable state of the simulation system is selected, an adjustment plan for the target model is generated, and the current target model is optimized.
[0129] Specifically, the application example of this application provides the concept of network security situation inversion: This application applies the inversion technology to the network security situation awareness in the field of cyberspace for the first time, and defines the concept of network security situation inversion as well as the main technical content and methods. The application example of this application also provides a process of network security situation inversion: This application designs a process of network security situation inversion that includes target reconnaissance, obtaining local information of key targets, discovering decision rules with prior knowledge, establishing a target model, simulating and evaluating the target model and detection parameters, improving the target model through simulation and evaluation, and determining model parameters.
[0130] In summary, the network security situation inversion method provided by the application example of this application has at least the following beneficial effects:
[0131] (1) Applying the inversion technology theory to network security situation awareness: The inversion method has been widely studied and applied in differential equations and geophysics. It has also been widely studied and applied in parameter estimation, radar imaging, medical imaging, remote sensing and telemetry, spectrum estimation, radio direction finding, and signal intelligence extraction in the fields of automation, electronics, and electronic engineering. However, in the field of cyberspace and network security situation awareness technology, there is no relevant public research result on the use of inversion technology to infer the parameter values of the corresponding reconnaissance target through the observation values of the physical system to obtain the complete information of the reconnaissance target. The network security situation inversion technology proposed in this application can better solve the problem of difficulty in direct detection or incomplete detection information during target reconnaissance.
[0132] (2) Advantages of network security situation inversion technology
[0133] The inversion process of network security situation including modeling, reasoning calculation, detection verification, deduction and evaluation is proposed. Drawing on the concepts and connotations of inversion technology in the fields of geophysics and electronic engineering, the application is extended to the field of cyberspace security. A network security situation inversion model including target reconnaissance, target modeling based on prior knowledge, simulation deduction and evaluation, detection verification and other processes is proposed, forming a gradually accurate closed-loop process, providing a set of solutions for the accurate characterization of key targets.
[0134] Fully utilize artificial intelligence technology methods such as knowledge discovery and knowledge reasoning. In order to improve the information about the target, we can use prior knowledge to deduce and analogize on the basis of known reconnaissance intelligence, establish an information model about the target, predict and infer other unknown key information about the target, and then verify or correct it through simulation, calculation, evaluation and reconnaissance detection. Prior knowledge mainly comes from existing situation databases and expert knowledge, as well as information models about the target established in the early stage. Through knowledge discovery technology, we can establish a prior knowledge base, make full use of prior knowledge and artificial intelligence methods, deduce and infer new knowledge, and improve network security situation information.
[0135] Make full use of expert knowledge. In the network security situation inversion technology method, an expert knowledge base is established in advance as prior knowledge for the construction of the target model; in the process of model parameter inversion, a simulation deduction evaluation link is established to provide a simulation deduction environment. Based on the deduction process with automatic and expert participation, the correctness of the target model and its parameter values are evaluated, so that the target model can more realistically reflect the target.
[0136] The embodiment of the present application also provides an electronic device, which may include a processor, a memory, a receiver and a transmitter, wherein the processor is used to execute the network security situation inversion method mentioned in the above embodiment, wherein the processor and the memory may be connected via a bus or other means, such as by bus connection. The receiver may be connected to the processor and the memory via wired or wireless means.
[0137] The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.
[0138] As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the network security situation inversion method in the embodiment of the present application. The processor executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory, that is, the network security situation inversion method in the above method embodiment is implemented.
[0139] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0140] The one or more modules are stored in the memory, and when executed by the processor, perform the network security situation inversion method in the embodiment.
[0141] In some embodiments of the present application, the user equipment may include a processor, a memory, and a transceiver unit, which may include a receiver and a transmitter. The processor, memory, receiver, and transmitter may be connected through a bus system. The memory is used to store computer instructions, and the processor is used to execute the computer instructions stored in the memory to control the transceiver unit to send and receive signals.
[0142] As an implementation method, the functions of the receiver and the transmitter in the present application can be considered to be implemented through a transceiver circuit or a dedicated chip for transceiver, and the processor can be considered to be implemented through a dedicated processing chip, a processing circuit or a general chip.
[0143] As another implementation method, it is possible to use a general-purpose computer to implement the server provided in the embodiment of the present application, that is, to store the program code for implementing the functions of the processor, receiver, and transmitter in a memory, and the general-purpose processor implements the functions of the processor, receiver, and transmitter by executing the code in the memory.
[0144] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the aforementioned network security situation inversion method are implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.
[0145] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is specifically performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.
[0146] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.
[0147] In this application, the features described and / or illustrated for one embodiment may be used in the same manner or in a similar manner in one or more other embodiments, and / or combined with or replace the features of other embodiments.
[0148] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims
1. A network security situation inversion method, characterized in that: include: Based on the prior knowledge of historical network security situation, an initial system model is constructed to reflect the network security situation of the target information system; Performing target reconnaissance on the target information system, and modifying parameters of the initial system model according to corresponding target reconnaissance result data to obtain a corresponding target system model; Construct a simulation environment for the target system model, perform state simulation and deduction on the target system model in the simulation environment, and optimize and adjust the target system model according to the corresponding simulation and deduction results.
2. The network security situation inversion method according to claim 1 is characterized in that: The prior knowledge includes: A situation database for storing historical network security situation information, expert knowledge for reflecting historical network security situation, and historical system models corresponding to each type of historical information system.
3. The network security situation inversion method according to claim 2 is characterized in that: The method of constructing an initial system model for reflecting the network security situation of the target information system based on the prior knowledge of the historical network security situation includes: Get the type of target information system; It is determined whether the historical information systems of various types contain a historical information system of the same type as the target information system. If so, the historical system model corresponding to the historical information system is used as the initial system model corresponding to the target information system.
4. The network security situation inversion method according to claim 3 is characterized in that: Also includes: If the historical information systems of various types are different from the target information system type, knowledge discovery processing is performed on the situation database based on a preset artificial intelligence algorithm to obtain decision rule data for constructing an initial system model corresponding to the target information system, and / or decision rule data for constructing an initial system model corresponding to the target information system is constructed based on the expert knowledge; An initial system model corresponding to the target information system is constructed based on the decision rule data.
5. The network security situation inversion method according to claim 1 is characterized in that: The target information system is reconnaissance-tested and the initial system model is modified according to corresponding target reconnaissance result data to obtain a corresponding target system model, including: Conducting target reconnaissance on the target information system based on a preset target reconnaissance method to obtain various types of parameter information used to reflect the network security situation of the target information system, wherein the various types of parameter information used to reflect the network security situation of the target information system include: the IP address, host information, network information, user information, information about the organization to which the user belongs, business relationship, and network security vulnerability information of the target information system; The initial system model is modified according to the parameter information to obtain a corresponding target system model.
6. The network security situation inversion method according to claim 1 is characterized in that: The step of constructing a simulation environment for the target system model, performing state simulation and deduction on the target system model in the simulation environment, and optimizing and adjusting the target system model according to corresponding simulation and deduction results includes: Simulating the target system model to form a simulation environment with an interactive interface; receiving simulated access point information sent by a user from the interactive interface, and setting different access points for the target system model in the simulation environment according to the simulated access point information, so that the user can perform state simulation deduction on the target system model in the simulation environment according to each of the access points to obtain different system states corresponding to the target system model; Performing state evaluation on each of the system states respectively, and selecting one of the system states as the optimal system state based on the corresponding state evaluation result, the prior knowledge and the target detection result data, and generating a corresponding adjustment plan based on the optimal system state; The target system model is optimized and adjusted based on the adjustment scheme.
7. The network security situation inversion method according to any one of claims 1 to 6, characterized in that: The target system model is used to represent the IP, host information, network information, user information, user organization information, business relationships and network security vulnerability information of the target information system.
8. A network security situation inversion device, characterized in that: include: A model building module, used to build an initial system model for reflecting the network security situation of the target information system based on the prior knowledge of the historical network security situation; A parameter correction module is used to perform target reconnaissance on the target information system and perform parameter correction on the initial system model according to the corresponding target reconnaissance result data to obtain a corresponding target system model; The model inversion module is used to construct a simulation environment for the target system model, and perform state simulation and deduction on the target system model in the simulation environment, and optimize and adjust the target system model according to the corresponding simulation and deduction results.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the network security situation inversion method as described in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the network security situation inversion method as described in any one of claims 1 to 7 is implemented.
