CN116318878A - Assessment method for security risk of power information network - Google Patents

Assessment method for security risk of power information network Download PDF

Info

Publication number
CN116318878A
CN116318878A CN202310123507.5A CN202310123507A CN116318878A CN 116318878 A CN116318878 A CN 116318878A CN 202310123507 A CN202310123507 A CN 202310123507A CN 116318878 A CN116318878 A CN 116318878A
Authority
CN
China
Prior art keywords
data
fuzzy
evaluation
security risk
fnn
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310123507.5A
Other languages
Chinese (zh)
Inventor
李国要
周健
方丽萍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Jiyuan Examination And Detection Technology Co ltd
Original Assignee
Anhui Jiyuan Examination And Detection Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anhui Jiyuan Examination And Detection Technology Co ltd filed Critical Anhui Jiyuan Examination And Detection Technology Co ltd
Priority to CN202310123507.5A priority Critical patent/CN116318878A/en
Publication of CN116318878A publication Critical patent/CN116318878A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
    • H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
    • H04L63/1416—Event detection, e.g. attack signature detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/048—Fuzzy inferencing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/142—Network analysis or design using statistical or mathematical methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
    • H04L63/1433—Vulnerability analysis
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/20—Network architectures or network communication protocols for network security for managing network security; network security policies in general
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Computer Hardware Design (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Optimization (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Pure & Applied Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Mathematical Analysis (AREA)
  • Algebra (AREA)
  • Automation & Control Theory (AREA)
  • Fuzzy Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of network security of power systems, in particular to an assessment method of power information network security risk. The security risk assessment includes the steps of: step one: data acquisition and processing; measuring and evaluating original data by an information security risk evaluation tool, and preprocessing the data; step two: carrying out fuzzy normalization on data; fuzzy normalization is carried out on each parameter, so that the data provided for the FNN intelligent learning reasoning process is normalized and fuzzified; step three: intelligent learning reasoning; each sub FNN is evaluated according to the processed data, and the result is used as the input of the previous stage FNN, so that the comprehensive evaluation of the security risk of the information system is finally realized. The method is based on the fuzzy neural network to learn training and risk rule interpretation, so that a risk assessment report of an energy internet system is generated, and further analysis and management of safety risks and vulnerability in the power information network are achieved.

Description

Assessment method for security risk of power information network
Technical Field
The invention relates to the technical field of network security of power systems, in particular to an assessment method of power information network security risk.
Background
Information infrastructure has now become the foundation of modern society. The localization of software and hardware products is an important condition for guaranteeing information security, and the information technology can enhance the national core competitiveness. Under the background of globalization of economy and daily and monthly variation of information communication technology, the information technology capability of the information technology and the capability of maintaining national security are closely connected together in all countries of the world, the development of the information technology industry has become a competitive focus for constructing comprehensive national power in the future in all countries of the world in a new period, and the important task of breaking through and grasping core technology and accelerating the development of the information technology industry is the construction work of a national information security guarantee system.
The network security of each company unit is provided with a certain number of network vulnerability scanners, and the network security scanner mainly comprises main stream products such as a green allied missing scanner, a stars missing scanner and the like. The product identifies the network asset based on the active scanning detection mode to determine the information of the asset operating system version, the middleware version and the like, and accordingly the information is associated and matched with the known vulnerability database to identify the hidden trouble of the vulnerability of the information network asset. However, the active scanning detection mode occupies large network resources and can have a certain influence on the continuity of network asset business, thereby seriously affecting the safe and stable operation of company business. Therefore, the overall utilization rate of the vulnerability scanner in the company range is relatively low at present, which also causes the problem that hidden dangers of the company are not mastered timely. Meanwhile, the scanner mainly identifies asset loopholes based on a version matching mode, and under the condition that network operation and maintenance personnel install relevant patches, the scanner cannot identify whether the patches are effective or not, and alarm of loopholes information is still carried out, so that the situation that companies grasp the security protection level of a service system inaccurately is caused, and intelligent and accurate loophole hidden danger judging and verifying technology is needed to be developed.
Disclosure of Invention
(one) solving the technical problems
In order to solve the problems in the prior art, the invention provides a method for evaluating the security risk of a power information network, and a network security risk analysis method based on big data and artificial intelligence is researched aiming at the characteristics of huge scale, complex structure and large access quantity of the power information network. Based on big data statistics and expert experience analysis, the safety risk analysis of elements including a network system, information assets, a Web system, interactive data and the like in the electric power energy interconnection system is researched, and a safety risk assessment technology based on data mining and artificial intelligence technology is researched on the basis. And carrying out data abstraction mapping and fuzzy cluster analysis on each part in the network system, carrying out learning training and risk rule interpretation on the parts based on the fuzzy neural network, and further generating a risk assessment report of the energy interconnection network system, so as to analyze and control safety risks and vulnerability in the power information network.
(II) technical scheme
In order to achieve the above purpose, the main technical scheme adopted by the invention comprises the following steps:
the method comprises the steps of firstly, carrying out abstract mapping and index extraction on risk factors of various power information systems, carrying out data preprocessing such as data cleaning and data transformation on the risk factors, carrying out abstract data on various risk factors, and cleaning data by filling in missing values of corresponding attributes, smooth noise data and the like; then converting the information into a form suitable for recognition filtering by normalization and other methods, wherein the security risk assessment comprises the following steps:
step one: data acquisition and processing; measuring and evaluating original data by an information security risk evaluation tool, and preprocessing the data;
step two: carrying out fuzzy normalization on data; fuzzy normalization is carried out on each parameter, so that the data provided for the FNN intelligent learning reasoning process is normalized and fuzzified;
step three: intelligent learning reasoning; each sub FNN is evaluated according to the processed data, and the result is used as the input of the previous stage FNN, so that the comprehensive evaluation of the security risk of the information system is finally realized.
Preferably, in the first step, the original evaluation data are screened, sorted and clustered, a fuzzy clustering principle is introduced, a reasonable factor evaluation set is established, n samples are respectively divided into c categories, and each sample is made to be
Figure SMS_1
The error square sum of the sample and the class mean value of the sample is minimum, and the fuzzy clustering objective function is described as follows: />
Figure SMS_2
In the formula u jk ＝uX i (z k ) For sample z k And subset z i (1.ltoreq.i.ltoreq.c); m is a weighted index, typically taken as 2; d, d ik For the cluster center p of the sample and the i-th class i A distance therebetween;
(d ik ) 2 ＝||z k -p i||A ＝(z k -p i ) T (z k -p i )；
the clustering criterion is to take J m Minimum value min { J of (U, P) m (U, P) } such that J m (U, P) is the smallest U ik A value;
Figure SMS_3
Figure SMS_4
in the formula I k ＝{i dik =0 }, such that J m (U, P) is the smallest P i The value of the sum of the values,
Figure SMS_5
the safety risk factors and the sub factors of the electric power information system are described by an evaluation set D= { low, medium, high and high }, on the basis of determining factor evaluation types by a fuzzy clustering method, aiming at the characteristics of FNN safety risk evaluation, regarding sub evaluation models of main evaluation FNN and subordinate FNN, related risk evaluation knowledge is required to be expressed in a form of fuzzy rules, and then a learning training sample of the FNN is established according to the fuzzy rules, wherein evaluation factors are required to be subjected to fuzzification in the fuzzy rules of the safety risk evaluation of the information system.
Preferably, each layer FNN adopts a fuzzy BP network structure, and input layer fuzzification neurons of each network carry out fuzzification processing on algorithms given by the upper section of the application of evaluation factors according to a fuzzy set F= { low, medium, high and high }.
Preferably, in the third step, each FNN adopts a three-layer fuzzy BP network.
Preferably, hidden layer neurons in FNN use modified generalized probability product type fuzzy neurons FN, and output layer neurons use modified generalized probability and fuzzy neurons FN.
Preferably, in information security risk assessment, the function of asset, threat and vulnerability is r=g (c, t, f), where c is the asset impact; t is threat frequency to the system; f is the vulnerability severity.
(III) beneficial effects
The invention provides an assessment method for security risk of an electric power information network. The beneficial effects are as follows:
(1) The intelligent power grid information system in the energy interconnection mode has complex safety-related data modes and huge data quantity, and is difficult to comprehensively and effectively carry out safety maintenance and defense by means of a single safety analysis and evaluation means. Aiming at the problem, the method comprehensively analyzes heterogeneous data in various modes including network risk analysis data, asset safety hidden danger data, safety attack and defense detection data, a safety vulnerability database and a patch database, and establishes an intelligent defense treatment framework of the safety vulnerability based on artificial intelligent technologies such as deep learning, thereby providing theory and strategy support for safety defense processes such as risk analysis, vulnerability rule mining, repair reinforcement and the like of the safety vulnerability life cycle of the electric power information system.
(2) The safety situation of the power information system with the energy interconnection is more and more severe, and the detection and repair response processes of the potential safety hazard are required to be quick and effective, so that the comprehensive safety response repair service and specification are provided for the safety hazard treatment process, and the comprehensive safety response repair service and specification have important significance for improving the safety of the power information system. Aiming at the problem, the problem establishes a vulnerability hidden safety response service resource library of the intelligent power grid information system, establishes a safety vulnerability management and control response mechanism of the power information system on the basis, and provides a corresponding safety vulnerability reinforcement and repair flow, thereby providing more efficient real-time repair response service for the safety defense process in the energy interconnection process.
Drawings
FIG. 1 is a flow chart of a Fuzzy Neural Network (FNN) information system security risk assessment process according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the present invention provides a technical solution: before the security risk analysis of the power information system, abstract mapping and index extraction are firstly carried out on risk factors of various power information systems, and data preprocessing such as data cleaning and data transformation is carried out on the risk factors. In order to improve the risk analysis quality and reduce the time complexity, firstly, aiming at various risk factor abstract data, cleaning data such as missing values of corresponding attributes, smooth noise data and the like are filled in; and then converted into a form suitable for recognition filtering by normalization and the like.
Application information systemAnd the system security risk assessment tool can acquire the assessed effective data information by combining expert knowledge and historical experience. In order to finish screening, sorting and clustering of the original evaluation data, a reasonable factor evaluation set is established, and a fuzzy clustering principle is introduced. In order to finish screening, sorting and clustering of the original security risk assessment data, a reasonable factor evaluation set is established, and a fuzzy clustering principle is introduced. The purpose of the dynamic clustering method is to divide n samples into c categories respectively to make each
Figure SMS_6
The sum of the squares of the errors of the sample and the mean of the class in which the sample is located is minimal. The general objective function of fuzzy clustering is described as:
Figure SMS_7
in the formula u jk ＝uX i (z k ) For sample z k And subset z i (1.ltoreq.i.ltoreq.c); m is a weighted index, typically taken as 2; d, d ik For the cluster center p of the sample and the i-th class i A distance therebetween;
(d ik ) 2 ＝||z k -p i||A ＝(z k -p i ) T (z k -p i )；
the clustering criterion is to take J m Minimum value min { J of (U, P) m (U, P) } such that J m (U, P) is the smallest U ik A value;
Figure SMS_8
Figure SMS_9
in the formula I k ＝{i dik =0 }, such that J m (U, P) is the smallest P i The value of the sum of the values,
Figure SMS_10
based on the above principle, the security risk factor of the power information system and its sub-factors are described by the evaluation set d= { low, medium, high }. Based on the determination of factor evaluation category by fuzzy clustering method, aiming at the characteristics of fuzzy neural network security risk evaluation, the related risk evaluation knowledge is expressed in the form of fuzzy rule for the sub-evaluation models of the main evaluation fuzzy neural network and the subordinate fuzzy neural network, and then a learning training sample of the fuzzy neural network is established according to the fuzzy rule. In the information system security risk assessment fuzzy rule, assessment factors need to be subjected to fuzzification processing.
The acquisition of the training sample set is a very important and very difficult loop in the security risk assessment by using the neural network, and the training sample set is established by combining a great amount of expert knowledge about the risk assessment and carrying out statistical analysis on big data. The fuzzy neural network adopts a learning strategy of a hierarchical system, and each fuzzy neural network subsystem is independently trained, so that the training process can be effectively accelerated. In each fuzzy neural network subsystem, the fuzzification function is realized by the fuzzification neurons, and the fuzzification neurons are also used as input layer nodes of the whole neural network system at the same time because the input layer neurons of the fuzzy neural network system only play a role of receiving network input data and have no calculation function. The fuzzy neural network of each layer adopts a fuzzy BP network structure, and the fuzzy neurons of the input layer of each network carry out fuzzy processing on the algorithm given by the upper section of the evaluation factor application according to a fuzzy set F= { low, medium, high and high }. The hidden layer neurons adopt modified generalized probability product type fuzzy neurons FN, and the output layer neurons adopt modified generalized probability and fuzzy neurons FN.
In this application: the Fuzzy Neural Network (FNN) is the product of combining the fuzzy theory and the neural network, integrates the advantages of the neural network and the fuzzy theory, and integrates learning, association, identification and information processing. The FNN in the text is represented as a fuzzy neural network.
And carrying out security risk assessment on a certain intelligent power grid information system. The system is a network composed of a central switch, a router, a security management center and a plurality of servers, and the effectiveness of the method is illustrated by constructing a fuzzy BP network model of a software facility for security risk assessment. The network topology structure and five kinds of risk factors are respectively a computer operating system, a network communication protocol, a general application platform and network management software. The fuzzy BP network model input layer is provided with 5 nodes, and the corresponding input is the fuzzy quantized values of the 5 security risk subfractions; the output layer has 1 node, and the corresponding output is a fuzzy evaluation value of the security risk of the software facility; according to the empirical formula in the literature, the number of nodes of the hidden layer is set to l=n-m+a, where a is a number between 1 and 10. The transfer functions between the input layer and the hidden layer and between the hidden layer and the output layer adopt logarithmic Sigmoid functions, namely, input data are preprocessed before the Sigmoid functions act. The training function of the network employs a trail () function, corresponding to a modified algorithm employing the Levenberg-Marquardt method. The performance function adopts a mean square error performance function mse (), and meanwhile, the average output square error e of sample training and the learning rate a thereof can be set according to actual application needs and field environments. In order to ensure the accuracy and network performance of network training, multiple groups of training samples of the security risk factors of the power information system can be selected by combining expert knowledge related to risk assessment and actual experience and assessment criteria of information system operation, and meanwhile, the initial termination method is adopted to improve the generalization capability of the network, ensure that the output result can approach to a true value with higher accuracy, and give a security risk analysis report of the whole network architecture by analyzing, explaining and refining the output result.
Based on the unique advantages of the neural network in the numerical parallel calculation of the complex system and the strong capability of the fuzzy system in the processing of expert knowledge and experience, the fuzzy theory is combined with the neural network to establish an assessment model aiming at the safety risk of the information system, and the model and the algorithm are tested through data simulation. The hierarchical assessment model realized by the fuzzy neural network is not only beneficial to learning new information system security risk assessment knowledge, but also has stronger generalization capability, can effectively degrade the security risk assessment problem of a complex information system, improves the performance of system risk assessment, and enhances the operability.
Based on the unique advantages of the neural network in the numerical parallel calculation of the complex system and the strong capability of the fuzzy system in the processing of expert knowledge and experience, the fuzzy theory is combined with the neural network to establish an assessment model aiming at the safety risk of the information system, and the model and the algorithm are tested through data simulation. The hierarchical assessment model realized by using the MFNN is not only beneficial to learning new information system security risk assessment knowledge, but also has stronger generalization capability, can effectively degrade the security risk assessment problem of the complex information system, and improves the performance and operability of system risk assessment.

Claims (6)

1. The assessment method of the security risk of the electric power information network is characterized by comprising the following steps of: firstly, abstract mapping and index extraction are carried out on risk factors of various power information systems, data preprocessing such as data cleaning and data transformation is carried out on the risk factors, and cleaning data such as missing values, smooth noise data and the like of corresponding attributes are filled in on abstract data of various risk factors; then converting the information into a form suitable for recognition filtering by normalization and other methods, wherein the security risk assessment comprises the following steps:
step one: data acquisition and processing; measuring and evaluating original data by an information security risk evaluation tool, and preprocessing the data;
step two: carrying out fuzzy normalization on data; fuzzy normalization is carried out on each parameter, so that the data provided for the FNN intelligent learning reasoning process is normalized and fuzzified;
step three: intelligent learning reasoning; each sub FNN is evaluated according to the processed data, and the result is used as the input of the previous stage FNN, so that the comprehensive evaluation of the security risk of the information system is finally realized.
2. The method for evaluating the security risk of the power information network according to claim 1, wherein the method comprises the following steps: screening, sorting and clustering original evaluation data, introducing a fuzzy clustering principle, establishing a reasonable factor evaluation set, and dividing n samples into c categories respectively to enable each sample to be in a different category
Figure FDA0004080949330000011
The error square sum of the sample and the class mean value of the sample is minimum, and the fuzzy clustering objective function is described as follows: />
Figure FDA0004080949330000012
In the formula u jk ＝uX i (z k ) For sample z k And subset z i (1.ltoreq.i.ltoreq.c); m is a weighted index, typically taken as 2; d, d ik For the cluster center p of the sample and the i-th class i A distance therebetween;
(d ik ) 2 ＝||z k -p i||A ＝(z k -p i ) T (z k -p i )；
the clustering criterion is to take J m Minimum value min { J of (U, P) m (U, P) } such that J m (U, P) is the smallest U ik A value;
Figure FDA0004080949330000013
Figure FDA0004080949330000021
in the formula I k ＝{i dik =0 }, such that J m (U, P) is the smallest P i The value of the sum of the values,
Figure FDA0004080949330000022
the safety risk factors and the sub factors of the electric power information system are described by an evaluation set D= { low, medium, high and high }, on the basis of determining factor evaluation types by a fuzzy clustering method, aiming at the characteristics of FNN safety risk evaluation, regarding sub evaluation models of main evaluation FNN and subordinate FNN, related risk evaluation knowledge is required to be expressed in a form of fuzzy rules, and then a learning training sample of the FNN is established according to the fuzzy rules, wherein evaluation factors are required to be subjected to fuzzification in the fuzzy rules of the safety risk evaluation of the information system.
3. The method for evaluating the security risk of the power information network according to claim 1, wherein the method comprises the following steps: and each layer of FNN adopts a fuzzy BP network structure, and input layer fuzzification neurons of each network carry out fuzzification processing on an algorithm given by an upper section of evaluation factor application according to a fuzzy set F= { low, medium, high and high }.
4. The method for evaluating the security risk of the power information network according to claim 1, wherein the method comprises the following steps: and in the third step, each FNN adopts a three-layer fuzzy BP network.
5. The method for evaluating the security risk of the power information network according to claim 1, wherein the method comprises the following steps: hidden layer neurons in FNN adopt modified generalized probability product type fuzzy neurons FN, and output layer neurons adopt modified generalized probability and fuzzy neurons FN.
6. The method for evaluating the security risk of the power information network according to claim 1, wherein the method comprises the following steps: in information security risk assessment, the functions of asset, threat and vulnerability are r=g (c, t, f), where c is the asset impact; t is threat frequency to the system; f is the vulnerability severity.
CN202310123507.5A 2023-02-07 2023-02-07 Assessment method for security risk of power information network Pending CN116318878A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310123507.5A CN116318878A (en) 2023-02-07 2023-02-07 Assessment method for security risk of power information network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310123507.5A CN116318878A (en) 2023-02-07 2023-02-07 Assessment method for security risk of power information network

Publications (1)

Publication Number Publication Date
CN116318878A true CN116318878A (en) 2023-06-23

Family

ID=86833356

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310123507.5A Pending CN116318878A (en) 2023-02-07 2023-02-07 Assessment method for security risk of power information network

Country Status (1)

Country Link
CN (1) CN116318878A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116703165A (en) * 2023-08-03 2023-09-05 国网山西省电力公司营销服务中心 Electric power metering data security risk assessment method and device

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116703165A (en) * 2023-08-03 2023-09-05 国网山西省电力公司营销服务中心 Electric power metering data security risk assessment method and device
CN116703165B (en) * 2023-08-03 2024-01-19 国网山西省电力公司营销服务中心 Electric power metering data security risk assessment method and device

Similar Documents

Publication Publication Date Title
CN106778259B (en) Abnormal behavior discovery method and system based on big data machine learning
CN105117602B (en) A kind of metering device running status method for early warning
CN107274105B (en) Linear discriminant analysis-based multi-attribute decision tree power grid stability margin evaluation method
CN114548637A (en) AHP-RST-based power communication backbone data network security comprehensive evaluation method
CN110213222A (en) Network inbreak detection method based on machine learning
CN112910859B (en) Internet of things equipment monitoring and early warning method based on C5.0 decision tree and time sequence analysis
CN114580706A (en) Power financial service wind control method and system based on GRU-LSTM neural network
Wang et al. Dealing with alarms in optical networks using an intelligent system
CN111598179A (en) Power monitoring system user abnormal behavior analysis method, storage medium and equipment
CN108549907A (en) A kind of data verification method based on multi-source transfer learning
CN116318878A (en) Assessment method for security risk of power information network
CN112241606A (en) Cooperative decision-making method for operation and maintenance of ship intelligent equipment based on CPS decision-making module
Wang et al. Extract rules from software quality prediction model based on neural network
CN109871711B (en) Ocean big data sharing and distributing risk control model and method
CN116545679A (en) Industrial situation security basic framework and network attack behavior feature analysis method
Jingyu et al. Statistical analysis of distribution network fault information based on multi-source heterogeneous data mining
Mangina et al. The use of a multi-agent paradigm in electrical plant condition monitoring
Liu Effective combination and application path of computer big data analysis and cloud computing network technology
CN117172721B (en) Data flow supervision early warning method and system for financing service
CN117792933B (en) Network flow optimization method and system based on deep learning
Luo [Retracted] Electronic Communication Fault Signal Recognition Based on Data Mining Algorithm
Subach et al. Models of Fuzzy Identification of Cyber Incidents in Information and Communication Systems by Intelligent SIEM Systems.
CN117240511A (en) Power grid terminal abnormality detection method
Yang A Security Evaluation Method for Complex Computer Networks Based on GABP Algorithm
Sun Platform Design of Project Bidding System on the Basic of TCM-KNN and Genetic Algorithm

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination