Power system exposed surface safety risk assessment method and related device

Abstract

The invention belongs to the field of power system security, and discloses a power system exposed surface security risk assessment method and a related device, and the method comprises the steps: constructing an information abstract model of a business scene according to the business scene and the structure topology of a power system, and obtaining risk elements of each exposed surface interface of the business scene based on the information abstract model; constructing a Bayesian attack graph of the business scene according to the information abstract model and the risk elements of each exposed surface interface, and obtaining a possible attack path and an attack probability of the possible attack path based on the Bayesian attack graph; and obtaining a security risk assessment result of the service scene through a pre-trained security assessment model according to the power system data, the possible attack path and the attack probability of the possible attack path. The method can effectively solve the problem that the accuracy and comprehensiveness of safety assessment are low because the safety risk assessment of the exposed surface of the electric power system is difficult to comprehensively cover the risk of the exposed surface at present, and can provide indexes and references for the safety risk assessment of the exposed surface of the electric power system.

Description

Technical Field

[0001] The present invention belongs to the field of power system safety, and relates to a power system exposed surface safety risk assessment method and related devices. Background Art

[0002] With the rapid development of smart grids and new power systems, the interactions between business systems, control systems, edge devices, and external systems involved in power systems are becoming increasingly complex, resulting in increased system exposure and significantly increased security risks. Electricity is a critical infrastructure, and its security is of vital importance. Electricity is often one of the important targets of cyber attacks. At the same time, attacks on power systems are often highly customized and highly concealed, so it is crucial to conduct security risk assessments on power systems to ensure their safe operation.

[0003] However, current power system exposure safety risk assessment methods mostly focus on single-dimensional risk analysis. For example, they usually only focus on whether there are loopholes in a single aspect. It is difficult to fully cover the multi-dimensional exposure risks in new power systems and cannot effectively assess various safety risks in new power systems. As a result, the accuracy and comprehensiveness of safety assessments are low, and effective optimization response measures cannot be provided. Summary of the invention

[0004] The purpose of the present invention is to overcome the above-mentioned shortcomings of the prior art and provide a method for assessing the safety risks of exposed surfaces of a power system and related devices.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for assessing the security risks of exposed surfaces of a power system, comprising: constructing an information abstraction model of a business scenario based on the business scenario and structural topology of the power system, and obtaining risk factors of each exposed surface interface of the business scenario based on the information abstraction model; constructing a Bayesian attack graph of the business scenario based on the information abstraction model and the risk factors of each exposed surface interface, and obtaining possible attack paths and attack probabilities of the possible attack paths based on the Bayesian attack graph; obtaining security risk assessment results of the business scenario through a pre-trained security assessment model based on power system data and possible attack paths and attack probabilities of the possible attack paths.

[0006] Optionally, the information abstraction model of constructing the business scenario according to the business scenario and structural topology of the power system includes: based on a preset power system business knowledge base, extracting corresponding elements and the relationships between corresponding elements according to the business scenario of the power system as nodes and edges of the information abstraction model, and merging repeated nodes and edges in the information abstraction model to obtain the final information abstraction model.

[0007] Optionally, the obtaining of risk factors of each exposed surface interface of a business scenario based on the information abstraction model includes: obtaining, based on the information abstraction model, each exposed surface interface and the interface type of each exposed surface interface contained in the information abstraction model; and obtaining the risk factors of each exposed surface interface according to the interface type of each exposed surface interface in combination with the information abstraction model.

[0008] Optionally, the interface types of the exposed surface interface are divided according to subject classification, interaction scenarios and authority attribution; the interface types of the exposed surface interface include: interfaces between business systems and external systems, interfaces between edge devices and external collection devices, interfaces between external collection devices and external systems, interfaces between business systems, interfaces between business systems and support platforms, interfaces between business systems and collection objects, interfaces between control systems, interfaces between control systems and external collection objects, interfaces between edge devices and internal collection devices, interfaces between edge devices and external systems, interfaces between control systems and business systems, interfaces involving power trading, user privacy, and interfaces between other subjects; the risk factors of each exposed surface interface include one or more of the following: code injection, man-in-the-middle attacks in file transfer protocols, structured query language injection, cross-site scripting attacks, cloud service discovery instance theft, signal interference, signal relaying, signal interception, signal tampering, signal replication, communication monitoring, key cracking, location-based attacks, malware, malicious domain name responses, additional certificate and proxy authority events, event subscription domain trust modifications, firewall modifications, log modifications, distributed denial of service attacks, and vulnerability exploits.

[0009] Optionally, the method of constructing a Bayesian attack graph for a business scenario based on the information abstraction model and the risk factors of each exposed surface interface, and obtaining possible attack paths and attack probabilities of possible attack paths based on the Bayesian attack graph includes: using Bayesian network theory to map the risk factors of each exposed surface interface and the dependencies between the nodes of the information abstraction model into the attack graph; wherein the nodes of the attack graph represent a system state or component, the edges represent possible state changes or attack actions, and the weights of the edges represent the probability of an attack occurring; setting conditional probabilities for each node and edge in the attack graph based on historical data to obtain a Bayesian attack graph; traversing the Bayesian attack graph, exploring all possible attack paths along the edges in the Bayesian attack graph to obtain possible attack paths, and for each possible attack path, multiplying the probabilities of all edges on the possible attack path to obtain the attack probability of the possible attack path.

[0010] Optionally, it also includes: updating the conditional probability of each node and edge in the Bayesian attack graph based on real-time data within a preset time period.

[0011] Optionally, the security risk assessment results of the business scenario include one or more of the following: a security risk classification label, a security risk threat level, and a risk report; wherein the security risk classification label is whether it is safe or a specific security threat type; the security risk threat level includes several quantitative indicators; the risk report includes the security risk threat level of possible attack paths, path information, and recommended protection measures.

[0012] According to a second aspect of the present invention, a system for assessing the safety risk of exposed surfaces of a power system is provided, comprising: a risk factor determination module for constructing an information abstraction model of a business scenario based on the business scenario and structural topology of the power system, and obtaining risk factors of each exposed surface interface of the business scenario based on the information abstraction model; a path analysis module for constructing a Bayesian attack graph of the business scenario based on the information abstraction model and the risk factors of each exposed surface interface, and obtaining possible attack paths and attack probabilities of possible attack paths based on the Bayesian attack graph; a risk assessment module for obtaining safety risk assessment results of business scenarios through a pre-trained security assessment model based on power system data and possible attack paths and attack probabilities of possible attack paths.

[0013] According to a third aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned power system exposure surface safety risk assessment method when executing the computer program.

[0014] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned power system exposure surface safety risk assessment method are implemented.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The method for assessing the safety risk of the exposed surface of the power system of the present invention fully combines the actual business situation from the perspective of the business scenario, first constructs an information abstraction model of the business scenario, and obtains the risk factors of each exposed surface interface of the business scenario based on the information abstraction model, and can more comprehensively cover various types of safety risks in the power system through a complete and multi-dimensional risk factor analysis of each exposed surface interface, and then constructs a Bayesian attack graph of the business scenario according to the information abstraction model and the risk factors of each exposed surface interface, and obtains possible attack paths and attack probabilities of possible attack paths based on the Bayesian attack graph, so as to achieve rapid and comprehensive analysis of possible attack paths, and then combines the power system data to obtain the safety risk assessment results of the business scenario through a pre-trained safety assessment model, so as to achieve efficient and accurate safety assessment of complex power systems, improve the accuracy and comprehensiveness of safety risk assessment, and provide guidance for ensuring the safe operation of power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a method for assessing safety risks of an exposed surface of a power system according to an embodiment of the present invention.

[0017] Figure 2 This is an example diagram of an abstract model of power system information according to an embodiment of the present invention.

[0018] Figure 3 This is an example diagram of the classification and summary results of the exposed surface interfaces according to an embodiment of the present invention.

[0019] Figure 4 It is a structural block diagram of a power system exposure surface safety risk assessment system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] The present invention is further described in detail below in conjunction with the accompanying drawings: See also Figure 1 In one embodiment of the present invention, a method for assessing the safety risk of an exposed surface of a power system is provided, which is a safety assessment method that combines multi-dimensional exposure surface risk analysis with deep detection of attack graphs.

[0023] Specifically, the power system exposure surface safety risk assessment method of the present invention includes the following steps: S1: Build an information abstraction model of the business scenario based on the business scenario and structural topology of the power system, and obtain the risk factors of each exposed interface of the business scenario based on the information abstraction model; S2: Construct a Bayesian attack graph of the business scenario based on the information abstraction model and the risk factors of each exposure interface, and obtain possible attack paths and attack probabilities of possible attack paths based on the Bayesian attack graph; S3: Based on the power system data, possible attack paths, and the attack probabilities of possible attack paths, the security risk assessment results of the business scenarios are obtained through the pre-trained security assessment model.

[0024] The method for assessing the safety risk of the exposed surface of the power system of the present invention fully combines the actual business situation from the perspective of the business scenario, first constructs an information abstraction model of the business scenario, and obtains the risk factors of each exposed surface interface of the business scenario based on the information abstraction model, and can more comprehensively cover various types of safety risks in the power system through a complete and multi-dimensional risk factor analysis of each exposed surface interface, and then constructs a Bayesian attack graph of the business scenario according to the information abstraction model and the risk factors of each exposed surface interface, and obtains possible attack paths and attack probabilities of possible attack paths based on the Bayesian attack graph, so as to achieve rapid and comprehensive analysis of possible attack paths, and then combines the power system data to obtain the safety risk assessment results of the business scenario through a pre-trained safety assessment model, so as to achieve efficient and accurate safety assessment of complex power systems, improve the accuracy and comprehensiveness of safety risk assessment, and provide guidance for ensuring the safe operation of power systems.

[0025] In a possible implementation, a power system business knowledge base is formed by collecting and organizing relevant information of all business systems, control systems, and collection objects involved in the power system, as well as interaction information between the subjects.

[0026] See also Figure 2, the information abstraction model of the business scenario constructed according to the business scenario and structural topology of the power system includes: based on the preset power system business knowledge base, extracting the corresponding elements and the relationship between the corresponding elements according to the business scenario of the power system as the nodes and edges of the information abstraction model, and merging the repeated nodes and edges in the information abstraction model to obtain the final information abstraction model. Specifically, by sorting and classifying various business system information and equipment information involved in the power system, including but not limited to dispatching automation system, distribution automation system, new generation centralized control station system, source network load storage collaborative interaction system, distribution cloud master station, OMS (Operation Management System, operation and maintenance management system), PMS (Production Management System, production management system), marketing business application system, new energy cloud, distribution IV zone master station, power consumption information collection system, smart energy service platform, Internet of Vehicles platform, external photovoltaic platform, control cloud, data middle platform, power grid resource business middle platform, real-time measurement center, etc. At the same time, it is also necessary to sort out the relevant edge devices, collection objects, external systems and other information and the interaction information between various subjects.

[0027] In a possible implementation, the method of obtaining risk factors of each exposed surface interface of a business scenario based on an information abstraction model includes: obtaining each exposed surface interface and the interface type of each exposed surface interface contained in the information abstraction model based on the information abstraction model; and obtaining risk factors of each exposed surface interface according to the interface type of each exposed surface interface in combination with the information abstraction model.

[0028] Specifically, the interface types of the exposed interface are divided according to factors such as subject classification, interaction scenario and authority attribution. Figure 3 In this implementation, the interface types of the exposed surface interface are divided into the following 13 categories: C1: interface between business system and external system, C2: interface between edge device and external collection device, C3: interface between external collection device and external system, C4: interface between business systems, C5: interface between business system and supporting platform, C6: interface between business system and collection object, C7: interface between control systems, C8: interface between control system and external collection object, C9: interface between edge device and internal collection device, C10: interface between edge device and external system, C11: interface between control system and business system, C12: interface involving power trading and user privacy, and C13: interface between other entities.

[0029] Then, for each type of exposed interface, we conduct research and analysis on common network security risk points. We can draw on some knowledge base vulnerability libraries and manually analyze risk points and risk factors. For example, for the interface between the business system and the external system, its risk points can be analyzed as follows: 1. Data sharing between multiple entities such as integrated energy services and virtual power plants still faces risks such as data ownership not being confirmed, classification and grading standards not being determined, and data leakage; 2. Self-built Internet monitoring platforms by external manufacturers are common, most of which are deployed on the Internet, with uneven security protection levels, and are easy to become attack springboards. Then, based on the results of the exposed interface classification and risk point analysis, we further refine the risk points and derive specific risk factors for the exposed interface.

[0030] In this implementation, risk factors include, but are not limited to, code injection, man-in-the-middle attacks in file transfer protocols, structured query language injection (SQL injection), cross-site scripting attacks (XSS attacks), cloud service discovery instance theft, signal interference, signal relaying, signal interception, signal tampering, signal replication, communication monitoring, key cracking, location-based attacks, malware, malicious domain name responses (malicious DNS responses), additional certificate and proxy authority events, event subscription domain trust modifications, firewall modifications, log modifications, distributed denial of service attacks (DDoS attacks), and vulnerability exploits.

[0031] Risk factors are mainly obtained based on risk point analysis. Risk points are analyzed based on corresponding interface types. Risk factors are analyzed based on risk points. Based on this, the risk factors of each exposed surface interface are realized according to the correspondence between the interface types of each exposed surface interface, and the information can be stored in a preset power system business knowledge base. Then, the risk factors of each exposed surface interface can be obtained according to the interface type of each exposed surface interface combined with the preset power system business knowledge base.

[0032] In a possible implementation, the Bayesian attack graph of the business scenario is constructed according to the information abstraction model and the risk factors of each exposure surface interface, and the possible attack paths and the attack probabilities of the possible attack paths are obtained based on the Bayesian attack graph, including: using Bayesian network theory to map the risk factors of each exposure surface interface and the dependencies between the nodes of the information abstraction model into the attack graph; wherein the nodes of the attack graph represent a system state or component, the edges represent possible state changes or attack actions, and the weights of the edges represent the probability of an attack; conditional probabilities are set for each node and edge in the attack graph based on historical data to obtain a Bayesian attack graph; by traversing the Bayesian attack graph, all possible attack paths are explored along the edges in the Bayesian attack graph to obtain possible attack paths, and for each possible attack path, the probabilities of all edges on the possible attack path are multiplied to obtain the attack probability of the possible attack path.

[0033] Specifically, based on the new power system business knowledge base, according to the business scenarios and structural topology of the power system, the exposed surface interfaces are sorted out and the risk factors of the exposed surface interfaces are analyzed. Then, the Bayesian network theory is used to construct a Bayesian attack graph to represent and find possible attack paths and the attack probabilities of possible attack paths.

[0034] The construction of the Bayesian attack graph includes: using the Bayesian network theory to map the above risk factors and the dependencies between the abstract model nodes into the attack graph. Each node represents a system state or component, the edge represents a possible state change or attack action, and the edge weight represents the probability of an attack. Then, based on historical data and expert knowledge, conditional probabilities are set for each node and edge in the attack graph to reflect the possibility of an attack and the probability of a system state transition, thereby obtaining a Bayesian attack graph.

[0035] Then, by traversing the Bayesian attack graph, we can start from the initial state (such as the normal operation state of the system) and explore all possible paths along the directed edges in the graph. These paths are potential attack paths, that is, possible attack paths. Then, for each possible attack path, we can multiply the probabilities of all edges on the possible attack path to get the attack probability of the possible attack path.

[0036] In a possible implementation, the power system exposure surface security risk assessment method further includes: updating the conditional probability of each node and edge in the Bayesian attack graph based on real-time data within a preset time period.

[0037] Specifically, after the security assessment model runs in the actual environment for a period of time, a series of new security events or attack data will often be accumulated. These data are valuable resources because they can truly reflect the security situation and potential threat trends in the current environment. In order to make full use of this newly collected information, it can be fed back to the core analysis tool, the Bayesian attack graph. The key to this feedback mechanism is that it allows the various components in the Bayesian attack graph to be dynamically updated according to the latest data, including the conditional probabilities associated with each node and edge.

[0038] The update process not only involves fine-tuning the probabilities of existing nodes and edges, but may also include the introduction of new nodes and edges to reflect newly discovered security vulnerabilities, attack paths, or defense measures. Through this continuous learning and adaptation process, the Bayesian attack graph can maintain its accuracy and real-time performance, better reflecting the current network security situation. This dynamic optimization capability is crucial to building an efficient and reliable security assessment system, as it ensures that security defense strategies are always formulated and adjusted based on the latest and most accurate information.

[0039] In one possible implementation, the pre-trained security assessment model can be constructed based on a convolutional neural network, that is, by training the convolutional neural network model, it can learn and identify different attack patterns and their impacts. The construction process is mainly a more general convolutional neural network method, including data preprocessing (including collection, cleaning and feature extraction), network structure design (including input layer, convolution layer, activation layer, fully connected layer and output layer, etc.) and model training (including training with labeled data sets and then verification testing).

[0040] The input of the security assessment model usually includes power system data, such as network traffic data, system logs, and sensor data. After preprocessing, these data are input into the security assessment model in an appropriate form (such as a two-dimensional array). At the same time, the input data also contains data from the Bayesian attack graph, that is, possible attack paths and the attack probabilities of possible attack paths. The output of the security assessment model is the security risk assessment result under the business scenario of the power system. During the training process, the security assessment model uses the data provided by the Bayesian attack graph to optimize the model parameters by simulating attack scenarios and historical data, thereby improving its recognition ability and assessment accuracy of different attack modes.

[0041] In a possible implementation, the security risk assessment result of the business scenario includes one or more of the following: a security risk classification label, a security risk threat level, and a risk report.

[0042] Specifically, the security risk classification label indicates whether the system is safe (such as safe and unsafe) or the specific threat type (such as SQL injection and DDoS attack, etc.). The security risk threat level includes several quantitative indicators to quantify the severity of the assessment results, usually expressed as a numerical value (such as 1 to 9) or a level (such as low, medium and high). The risk report includes the security risk threat level of possible attack paths, path information and recommended protection measures to support system operation and maintenance personnel in making the next step of power system security decisions.

[0043] Optionally, the risk report is displayed in the form of visualization or report to provide support for power system security protection and decision-making. At the same time, the Bayesian attack graph also provides an intuitive view to help system operators understand potential security threats and attack paths.

[0044] The power system exposure surface safety risk assessment method of the present invention can effectively solve the problems of the current power system exposure surface safety risk assessment, such as single assessment dimension and difficulty in comprehensively covering exposure surface risks, and can provide an index and reference for the power system exposure surface safety risk assessment.

[0045] The following are device embodiments of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0046] See also Figure 4 In yet another embodiment of the present invention, a power system exposure surface safety risk assessment system is provided, which can be used to implement the above-mentioned power system exposure surface safety risk assessment method.

[0047] Specifically, the power system exposure surface security risk assessment system includes a risk factor determination module, a path analysis module and a risk assessment module. Among them, the risk factor determination module is used to construct an information abstraction model of the business scenario according to the business scenario and structural topology of the power system, and obtain the risk factors of each exposure surface interface of the business scenario based on the information abstraction model; the path analysis module is used to construct a Bayesian attack graph of the business scenario according to the information abstraction model and the risk factors of each exposure surface interface, and obtain possible attack paths and attack probabilities of possible attack paths based on the Bayesian attack graph; the risk assessment module is used to obtain the security risk assessment results of the business scenario through a pre-trained security assessment model based on the power system data and possible attack paths and attack probabilities of possible attack paths.

[0048] In a possible implementation, the information abstraction model-based method for obtaining risk factors for each exposed surface interface of a business scenario includes: obtaining each exposed surface interface and the interface type of each exposed surface interface contained in the information abstraction model based on a preset power system business knowledge base combined with the information abstraction model; and obtaining the risk factors for each exposed surface interface based on the interface type of each exposed surface interface combined with the preset power system business knowledge base.

[0049] In a possible implementation, the Bayesian attack graph of the business scenario is constructed according to the information abstraction model and the risk factors of each exposure surface interface, and the possible attack paths and the attack probabilities of the possible attack paths are obtained based on the Bayesian attack graph, including: using Bayesian network theory to map the risk factors of each exposure surface interface and the dependencies between the nodes of the information abstraction model into the attack graph; wherein the nodes of the attack graph represent a system state or component, the edges represent possible state changes or attack actions, and the weights of the edges represent the probability of an attack; conditional probabilities are set for each node and edge in the attack graph based on historical data to obtain a Bayesian attack graph; by traversing the Bayesian attack graph, all possible attack paths are explored along the edges in the Bayesian attack graph to obtain possible attack paths, and for each possible attack path, the probabilities of all edges on the possible attack path are multiplied to obtain the attack probability of the possible attack path.

[0050] All relevant contents of each step involved in the embodiment of the aforementioned power system exposure surface safety risk assessment method can be referred to the functional description of the functional module corresponding to the power system exposure surface safety risk assessment system in the embodiment of the present invention, and will not be repeated here.

[0051] The division of modules in the embodiments of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into one processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0052] In another embodiment of the present invention, a computer device is provided, the computer device comprising a processor and a memory, the memory being used to store a computer program, the computer program comprising program instructions, and the processor being used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may 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 gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in a computer storage medium to implement a corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the power system exposure surface safety risk assessment method.

[0053] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in a computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for assessing the safety risk of the exposed surface of the power system in the above embodiment.

[0054] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0055] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0056] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0058] Finally, 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for assessing the safety risk of an exposed surface of a power system, characterized in that: include: Construct an information abstraction model of the business scenario based on the business scenario and structural topology of the power system, and obtain the risk factors of each exposed interface of the business scenario based on the information abstraction model; Construct a Bayesian attack graph for the business scenario based on the information abstraction model and the risk factors of each exposed interface, and obtain possible attack paths and the attack probabilities of possible attack paths based on the Bayesian attack graph; Based on the power system data, possible attack paths and the attack probabilities of possible attack paths, the security risk assessment results of the business scenarios are obtained through the pre-trained security assessment model.

2. The method for assessing the safety risk of an exposed surface of a power system according to claim 1, characterized in that: The information abstraction model for constructing the business scenario according to the business scenario and structural topology of the power system includes: Based on the preset power system business knowledge base, corresponding elements and the relationships between corresponding elements are extracted according to the business scenarios of the power system as nodes and edges of the information abstraction model, and the repeated nodes and edges in the information abstraction model are merged to obtain the final information abstraction model.

3. The method for assessing the safety risk of an exposed surface of a power system according to claim 1, characterized in that: The risk factors of each exposed interface of the business scenario obtained based on the information abstraction model include: Based on the information abstraction model, each exposed surface interface and the interface type of each exposed surface interface contained in the information abstraction model are obtained; and according to the interface type of each exposed surface interface and the information abstraction model, the risk factor of each exposed surface interface is obtained.

4. The method for assessing the safety risk of an exposed surface of a power system according to claim 3, characterized in that: The interface types of the exposed interface are divided according to subject classification, interaction scenario and authority attribution; The interface types of the exposed surface interface include: interfaces between business systems and external systems, interfaces between edge devices and external collection devices, interfaces between external collection devices and external systems, interfaces between business systems, interfaces between business systems and support platforms, interfaces between business systems and collection objects, interfaces between control systems, interfaces between control systems and external collection objects, interfaces between edge devices and internal collection devices, interfaces between edge devices and external systems, interfaces between control systems and business systems, interfaces involving power trading, user privacy, and interfaces between other entities; The risk factors of each exposed interface include one or more of the following: code injection, man-in-the-middle attack in file transfer protocol, structured query language injection, cross-site scripting attack, cloud service discovery instance theft, signal interference, signal relay, signal interception, signal tampering, signal replication, communication monitoring, key cracking, location-based attack, malware, malicious domain name response, additional certificate and proxy authority events, event subscription domain trust modification, firewall modification, log modification, distributed denial of service attack and vulnerability exploitation.

5. The method for assessing the safety risk of an exposed surface of a power system according to claim 1, characterized in that: The Bayesian attack graph of the business scenario is constructed according to the information abstraction model and the risk factors of each exposure interface, and the possible attack paths and the attack probabilities of the possible attack paths are obtained based on the Bayesian attack graph, including: Using Bayesian network theory, the risk factors of each exposure interface and the dependencies between nodes of the information abstraction model are mapped into the attack graph. The nodes of the attack graph represent a system state or component, the edges represent possible state changes or attack actions, and the weights of the edges represent the probability of an attack. Set conditional probabilities for each node and edge in the attack graph based on historical data to obtain a Bayesian attack graph; By traversing the Bayesian attack graph, all possible attack paths are explored along the edges in the Bayesian attack graph to obtain possible attack paths, and for each possible attack path, the probabilities of all edges on the possible attack path are multiplied to obtain the attack probability of the possible attack path.

6. The method for assessing the safety risk of an exposed surface of a power system according to claim 5, characterized in that: Also includes: Based on real-time data within a preset time period, the conditional probability of each node and edge in the Bayesian attack graph is updated.

7. The method for assessing the safety risk of an exposed surface of a power system according to claim 1, characterized in that: The security risk assessment results of the business scenario include one or more of the following: a security risk classification label, a security risk threat level, and a risk report; wherein the security risk classification label is whether it is safe or a specific security threat type; the security risk threat level includes several quantitative indicators; the risk report includes the security risk threat level of possible attack paths, path information, and recommended protection measures.

8. A power system exposure surface safety risk assessment system, characterized in that: include: A risk factor determination module is used to construct an information abstraction model of the business scenario according to the business scenario and structural topology of the power system, and obtain the risk factors of each exposed surface interface of the business scenario based on the information abstraction model; The path analysis module is used to construct a Bayesian attack graph of the business scenario based on the information abstraction model and the risk factors of each exposure interface, and obtain possible attack paths and attack probabilities of possible attack paths based on the Bayesian attack graph; The risk assessment module is used to obtain the security risk assessment results of the business scenario through a pre-trained security assessment model based on the power system data, possible attack paths and the attack probabilities of possible attack paths.

9. A computer 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 steps of the power system exposure surface security risk assessment method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for assessing the safety risk of the exposure surface of a power system as claimed in any one of claims 1 to 7 are implemented.

Images