CN109359469A - An information security risk assessment method for industrial control systems - Google Patents
An information security risk assessment method for industrial control systems Download PDFInfo
- Publication number
- CN109359469A CN109359469A CN201811203136.7A CN201811203136A CN109359469A CN 109359469 A CN109359469 A CN 109359469A CN 201811203136 A CN201811203136 A CN 201811203136A CN 109359469 A CN109359469 A CN 109359469A
- Authority
- CN
- China
- Prior art keywords
- risk assessment
- neural network
- training
- industrial control
- value
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012502 risk assessment Methods 0.000 title claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000013528 artificial neural network Methods 0.000 claims abstract description 32
- 238000013210 evaluation model Methods 0.000 claims abstract description 14
- 230000002068 genetic effect Effects 0.000 claims abstract description 12
- 230000009467 reduction Effects 0.000 claims abstract description 9
- 238000011156 evaluation Methods 0.000 claims abstract description 7
- 108090000623 proteins and genes Proteins 0.000 claims description 12
- 230000035772 mutation Effects 0.000 claims description 6
- 238000004886 process control Methods 0.000 claims description 6
- 210000000349 chromosome Anatomy 0.000 claims description 5
- 230000016571 aggressive behavior Effects 0.000 claims description 3
- 238000013213 extrapolation Methods 0.000 claims description 3
- 230000001537 neural effect Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 1
- 230000003612 virological effect Effects 0.000 claims 1
- 230000001186 cumulative effect Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 239000007787 solid Substances 0.000 description 4
- 241000700605 Viruses Species 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/57—Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
- G06F21/577—Assessing vulnerabilities and evaluating computer system security
-
- 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
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/03—Indexing scheme relating to G06F21/50, monitoring users, programs or devices to maintain the integrity of platforms
- G06F2221/034—Test or assess a computer or a system
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Physiology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明涉及一种工业控制系统的信息安全风险评估方法，包括以下步骤：S1、获取风险评估值及其对应多个风险评估要素的多组评估分数，作为初始样本数据集；S2、对初始样本数据采用KPCA处理，根据累计贡献率选取主成分，得到降维后的样本数据集；S3、将降维后的样本数据集作为训练样本，训练遗传算法优化的BP神经网络，得到预测模型；S4、将多个风险评估要素的评估分数输入预测模型中，得到风险评估值的预测值。与现有技术相比，本发明不仅改善了神经网络中参数选择的问题，还有效提高风险评估模型的评估精度，该风险评估模型为常规建模与智能方法的结合，对工业控制系统具有重要的意义。
The invention relates to an information security risk assessment method for an industrial control system, comprising the following steps: S1, obtaining a risk assessment value and multiple sets of assessment scores corresponding to multiple risk assessment elements, as an initial sample data set; S2, evaluating the initial sample The data is processed by KPCA, the principal components are selected according to the cumulative contribution rate, and the sample data set after dimension reduction is obtained; S3. The sample data set after dimension reduction is used as a training sample, and the BP neural network optimized by genetic algorithm is trained to obtain a prediction model; S4 . Input the assessment scores of multiple risk assessment elements into the prediction model to obtain the predicted value of the risk assessment value. Compared with the prior art, the present invention not only improves the problem of parameter selection in the neural network, but also effectively improves the evaluation accuracy of the risk evaluation model, which is a combination of conventional modeling and intelligent methods, and is of great importance to industrial control systems. meaning.
Description
Technical field
The present invention relates to field of information security technology, comment more particularly, to a kind of Information Security Risk of industrial control system
Estimate method.
Background technique
Industrial control system (Industrial Control System, abbreviation ICS) is widely used in petrochemical industry, hands over
In the national critical infrastructures such as logical transport, water process.As the development and " two change " fusion of information technology are goed deep into, tradition
Industrial control system and IT system, or even connect with Internet more and more closer, the security threat for causing ICS to face is continuous
Increase.
Since in recent years, the overall size of industrial control system gradually expands, and security level associated therewith also obtains
General Promotion.However should not ignore, industrial control system under the new situation remains difficult to eliminate Information Risk from source, therefore in visitor
Where the value for embodying risk assessment in sight.Information security risk evaluation applies to industrial control system at this stage, facilitates
Risk is judged and identified in the shorter period rapidly, then adequate measures is selected to be subject to prevention and control.It can be seen that information is pacified
Full assessment should be realized with the normal operation of industrial control system and is intimately associated, and can just be dedicated to preventing under the premise of the two combines comprehensively
It controls risk and eliminates wherein potential loophole.
For the whole system of Industry Control, risk assessment itself has the feature of architecture, thus constitutes and be
System engineering.From the point of view of essential characteristic, the core of risk assessment be to estimate industrial control system due to by various outside threats or
Resource lacks and bring evapotranspiration, is dedicated to assessing tender spots and threat degree in whole system under the premise of this.It opens
Open up comprehensive risk assessment, objective is to verify wherein potential every risk and crisis, thus adaptation to local conditions provide it is feasible
Property stronger security strategy, ensure safe operation.So under this kind of background, how to find and corresponding accurately comment
The method of estimating becomes urgent problem to be solved in present practice circle and academia.
Error backpropagation algorithm (Back Propagation, abbreviation BP) include signal propagated forward and error it is anti-
To propagate two processes, i.e., calculating error output when by from be input to output direction carry out, and adjust weight and threshold value then from
The direction for being output to input carries out.When forward-propagating, input signal acts on output node by hidden layer, by non-linear change
Generation output signal is changed, if reality output is not consistent with desired output, is transferred to the back-propagation process of error.Error-duration model is
By output error by hidden layer to the layer-by-layer anti-pass of input layer, and error distribution is given to all units of each layer, to obtain from each layer
Error signal as adjustment each unit weight foundation.By adjusting the linking intensity and hidden layer of input node and hidden node
The linking intensity and threshold value of node and output node, make error along gradient direction decline, by repetition learning training, determine with
The corresponding network parameter of minimal error (weight and threshold value), training stop stopping.Trained neural network can at this time
To the input information of similar sample, the smallest information by non-linear conversion of output error is voluntarily handled.BP neural network is
Most widely used prediction model, but there are two obvious disadvantages for the model: first is that easily falling into local minimum；Second is that convergence speed
Degree is slow.A kind of method for overcoming disadvantages mentioned above is optimized using Genetic Algorithms (Genetic Algorithm, genetic algorithm)
BP neural network prediction model.The randomness defect in BP neural network connection weight and threshold value selection is made up with GA, not only
The extensive mapping ability of BP neural network can be played, and makes BP neural network that there is faster convergence and stronger study
Ability.
Summary of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide a kind of industrial control systems
Information Security Risk Assessment Methods.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of Information Security Risk Assessment Methods of industrial control system, comprising the following steps:
S1, the multiple groups assessment score for obtaining risk assessment value and its corresponding multiple risk assessment elements, as initial sample
Data set；
S2, initial sample data set is handled using KPCA, principal component is chosen according to contribution rate of accumulative total, after obtaining dimensionality reduction
Sample data set；
S3, using the sample data set after dimensionality reduction as training sample, the BP neural network of training genetic algorithm optimization obtains
Risk evaluation model；
S4, the assessment score of multiple risk assessment elements is inputted in risk evaluation model, obtains the pre- of risk assessment value
Measured value.
Preferably, the contribution rate of accumulative total is not less than 90%.
Preferably, the step S3 is specifically included:
S31, population scale is set as P, generate the initial population W=(W of P individual at random1,W2,...,WP)T, give one
Data select range, generate individual W in population using linear interpolation functioniA real vector w1,w2,...,wSAs something lost
One chromosome of propagation algorithm, using real number coding method；
S32, the evaluation function for determining individual: giving a BP neural network evolution parameter, will contaminate obtained in step S31
Colour solid carries out assignment to BP neural network weight and threshold value, and input training sample carries out neural metwork training, reaches the essence of setting
Network training output valve is obtained after degree, using training error quadratic sum as population W in individual WiFitness；
S33, using roulette method selection operator, i.e., the selection strategy based on fitness ratio is to the dye in every generation population
Colour solid is selected, select probability are as follows:
Wherein: fiFor fitness value inverse；
S34, crossover operation, k-th of gene w are carried out using real number interior extrapolation methodkWith first of gene wkIn j crossover operations
It is respectively as follows:
wkj=wkj(1-b)+wljB,
wlj=wlj(1-b)+wkjb
Wherein, random number of the b between [0,1]；
S35: mutation operation: j-th of gene for choosing i-th of individual carries out mutation operation, it may be assumed that
F (g)=r2(1-g/Gmax)
Wherein: wmaxAnd wminRespectively gene wijThe bound of value, random number of the r between [0,1], r2It is random for one
Number, g are current iteration number, GmaxFor maximum evolutionary generation；
S36, the optimum individual for obtaining genetic algorithm are decomposed into the connection weight and threshold value of BP neural network, in this, as
The initial weight and threshold value of risk evaluation model.
Preferably, momentum term coefficient is 0.75 during the BP neural network of the trained genetic algorithm optimization, maximum
Frequency of training is 15000 times, target error 0.0002.
Preferably, the risk assessment element includes enterprise management level element, process control station element and field control layer
Element.
Preferably, the enterprise management level element includes: unauthorized access, malicious code, distributed denial of service, virus
Wooden horse and forgery attack；The process control station element includes: that Denial of Service attack, dos attack, extensive aggression, response are cheated
With direction misdirecting attack；The field control layer element includes: physical attacks, information stealth, data tampering, Denial of Service attack
It hits, unauthorized access and Replay Attack.
Compared with prior art, the present invention is based on KPCA-GA-BP to industrial control system information security risk evaluation, removes
It is predicted using ordinary BP nerve network, also it is optimized using genetic algorithm, searches out optimal initial weight and threshold
Value, the problem of keeping conventional model accuracy and generalization ability more preferable, not only improve parameter selection in neural network, also effectively mentions
The Evaluation accuracy of high risk assessment models, which is the combination of conventional modeling and intelligent method, to Industry Control
System has great importance.
Detailed description of the invention
Fig. 1 is the method for the present invention flow chart；
Fig. 2 is industrial control system risk elements structure chart in the present invention；
Fig. 3 be embodiment in tri- kinds of BP neural network, KPCA-BP neural network and KPCA-GA-BP of the present invention models most
Whole training result curve graph；
Fig. 4 be embodiment in tri- kinds of BP neural network, KPCA-BP neural network and KPCA-GA-BP of the present invention models most
Training relative error curve graph eventually；
Fig. 5 be embodiment in tri- kinds of BP neural network, KPCA-BP neural network and KPCA-GA-BP of the present invention models most
Training the number of iterations figure eventually.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to
Following embodiments.
Embodiment
The application proposes a kind of Information Security Risk Assessment Methods of industrial control system, according to industrial control system information
Safety-related standard analysis influences the factor of information security, and establishes corresponding structural model, determine each specific factor and by
Expert estimation assigns a value；KPCA processing is carried out to risk elements, and extracts principal component and obtains the sample data after dimensionality reduction；
Then risk evaluation model is obtained to GA-BP network training by sample data.
As shown in Figure 1, this method specifically includes the following steps:
S1, the multiple groups assessment score for obtaining risk assessment value and its corresponding multiple risk assessment elements, as initial sample
Data set；
According to " GB/T 35673-2017. industrial communication network network and system security technology safety requirements and safety etc.
Grade " and " GB/T 36466-2018 information security technology industrial control system risk assessment implementation guide " and industrial control system
Three Tiered Network Architecture, 16 risk assessment elements are listed, as shown in Fig. 2, including that enterprise management level element, process control station are wanted
Element and field control layer element；Enterprise management level element includes: unauthorized access, malicious code, distributed denial of service, virus
Wooden horse and forgery attack；Process control station element includes: Denial of Service attack, dos attack, extensive aggression, response is cheated and side
To misdirecting attack；Field control layer element includes: physical attacks, information stealth, data tampering, Denial of Service attack, illegal visit
It asks and Replay Attack；
In the present embodiment, the object of risk assessment is this 16 elements, and the value-at-risk of each element is by expert according to industry
" GA/T 1390.5-2017 information security technology network safety grade protects the 5th part of basic demand: industrial control system to standard
Security extension requirement " in the classification of risks standard that proposes specifically assessed, and characterized with integer of 1 to 10.
S2, initial sample data is handled using core principle component analysis (KPCA), principal component is chosen according to contribution rate of accumulative total,
Sample data set after obtaining dimensionality reduction in the present embodiment, extracts the contribution rate of accumulative total of principal component not less than 90%.
S3, the BP neural network for optimizing the sample data set after dimensionality reduction as training sample, training genetic algorithm (GA),
The pattern of fusion regression model based on BP neural network, i.e. GA-BP risk evaluation model are constructed, the survey of risk evaluation model is improved
Accuracy, specifically includes the following steps:
S31, population scale is set as P, generate the initial population W=(W of P individual at random1,W2,...,WP)T, give one
Data select range, generate individual W in population using linear interpolation functioniA real vector w1,w2,...,wSAs GA
A chromosome, high-precision weight and threshold value in order to obtain, using real number coding method；
S32, the evaluation function for determining individual: giving a BP neural network evolution parameter, will contaminate obtained in step S31
Colour solid carries out assignment to BP neural network weight and threshold value, and input training sample carries out neural metwork training, reaches the essence of setting
Network training output valve is obtained after degree, using training error quadratic sum as population W in individual WiFitness；
S33, using roulette method selection operator, i.e., the selection strategy based on fitness ratio is to the dye in every generation population
Colour solid is selected, select probability are as follows:
Wherein: fiFor fitness value inverse；
S34, real coding is used due to individual, crossover operation method uses real number interior extrapolation method, k-th of gene wkWith l
A gene wkIt is respectively as follows: in j crossover operations
Wherein, random number of the b between [0,1]；
S35: mutation operation: j-th of gene for choosing i-th of individual carries out mutation operation, it may be assumed that
F (g)=r2(1-g/Gmax)
Wherein: wmaxAnd wminRespectively gene wijThe bound of value, random number of the r between [0,1], r2It is random for one
Number, g are current iteration number, GmaxFor maximum evolutionary generation；
S36, the optimum individual for obtaining genetic algorithm are decomposed into the connection weight and threshold value of BP neural network, in this, as
The initial weight and threshold value of risk evaluation model obtain the corresponding regression function of risk evaluation model.
S4, the assessment score of multiple risk assessment elements is inputted in risk evaluation model, obtains the pre- of risk assessment value
Measured value.
It obtains 15 groups in the present embodiment for the validity for verifying modeling method and outputs and inputs data as nerve net
The learning sample of network.As shown in table 1, there are 16 risk assessment elements point (F1~F16) and the assessed value of 15 application systems, grade
It is not to be divided according to assessed value size, the object of risk assessment is this 16 elements.
1 15 systematic sample data of table
Table 2 is the specific data that KPCA analyzes result, as can be seen from Table 2, when proceeding to the 6th Principle component extraction,
Accumulative principal component contribution proportion total value has been above 90%, can represent 90% information of original 16 elements, so with
The data set that this 6 principal components generate replaces initial data as training sample, and this 6 principal components are irrelevant 6
A principal component.
2 KPCA of table analyzes result
In order to verify the validity based on KPCA-GA-BP Information Security Risk Assessment Methods of the application proposition, this implementation
Example carries out this method with based on BP neural network, the Information Security Risk Evaluation Model obtained based on KPCA-BP neural network
Comparative analysis.In the present embodiment, BP neural network, which uses, has training method of the momentum gradient descent method as network, and sets
Traingdm function is training function.Performance function is MSE function.Momentum term coefficient=0.75, maximum frequency of training are 15000
It is secondary, target error 0.0002.Sample data of the 12 groups of data of front as correlation training in table 1, is used for BP network,
4 groups of data of number 12 to 15 carry out risk data with trained BP network is had already passed through as verifying collection data below
Prediction, the operation being finally normalized obtain output valve.Prediction result can also be compared with truthful data.In order to avoid with
Machine, 3 kinds of models are separately operable 20 times, and prediction result is as shown in Fig. 3,4 and table 3.
The prediction result of the different risk evaluation models of table 3
Can be obtained by table 3, the range of the relative error rate for the model that this method obtains is 0.56%~1.03%, and other two
The relative error rate range of kind model is 1.11%~7.2 4%.So the neural network model obtained based on this method is to wind
The accuracy rate that danger is predicted is promoted, and can carry out risk assessment to industrial control system more accurately.
The operation time of the different risk evaluation models of table 4
| Network parameter | BP model | KPCA-BP model | KPCA-GA-BP model |
| The number of iterations | 11397 | 4103 | 2384 |
| Training time | 67 | 41 | 28 |
By Fig. 5 and table 4, it can be seen that if there is identical error learning objective, it is iterated based on this method modeling
Number and the duration of training are few more many than other two methods, so this method establishes the process of model in convergence rate
On be also improved.
Claims (3)
1. a kind of Information Security Risk Assessment Methods of industrial control system, which comprises the following steps:
S1, the multiple groups assessment score for obtaining risk assessment value and its corresponding multiple risk assessment elements, as initial sample data
Collection；
S2, initial sample data set is handled using KPCA, principal component is chosen according to contribution rate of accumulative total, the sample after obtaining dimensionality reduction
Data set；
S3, using the sample data set after dimensionality reduction as training sample, the BP neural network of training genetic algorithm optimization obtains risk
Assessment models；
S4, the assessment score of multiple risk assessment elements is inputted in risk evaluation model, obtains the predicted value of risk assessment value.
2. a kind of Information Security Risk Assessment Methods of industrial control system according to claim 1, which is characterized in that institute
Step S3 is stated to specifically include:
S31, population scale is set as P, generate the initial population W=(W of P individual at random1,W2,...,WP)T, give a data
Selected range generates individual W in population using linear interpolation functioniA real vector w1,w2,...,wSIt is calculated as heredity
One chromosome of method, using real number coding method；
S32, the evaluation function for determining individual: a BP neural network evolution parameter is given, by chromosome obtained in step S31
Assignment carried out to BP neural network weight and threshold value, input training sample carries out neural metwork training, after the precision for reaching setting
Obtain network training output valve, using training error quadratic sum as population W in individual WiFitness；
S33, using roulette method selection operator, i.e., the selection strategy based on fitness ratio is to the chromosome in every generation population
It is selected, select probability are as follows:
Wherein: fiFor fitness value inverse；
S34, crossover operation, k-th of gene w are carried out using real number interior extrapolation methodkWith first of gene wkDistinguish in j crossover operations
Are as follows:
wkj=wkj(1-b)+wljB,
wlj=wlj(1-b)+wkjb
Wherein, random number of the b between [0,1]；
S35: mutation operation: j-th of gene for choosing i-th of individual carries out mutation operation, it may be assumed that
F (g)=r2(1-g/Gmax)
Wherein: wmaxAnd wminRespectively gene wijThe bound of value, random number of the r between [0,1], r2For a random number, g
For current iteration number, GmaxFor maximum evolutionary generation；
S36, the optimum individual for obtaining genetic algorithm are decomposed into the connection weight and threshold value of BP neural network, in this, as risk
The initial weight and threshold value of assessment models.
3. a kind of Information Security Risk Assessment Methods of industrial control system according to claim 1, which is characterized in that institute
Stating risk assessment element includes enterprise management level element, process control station element and field control layer element；The business administration
Layer element includes: unauthorized access, malicious code, distributed denial of service, viral wooden horse and forgery attack；The process control
Layer element includes: that Denial of Service attack, dos attack, extensive aggression, response are cheated and direction misdirecting attack；The field control
Layer element includes: physical attacks, information stealth, data tampering, Denial of Service attack, unauthorized access and Replay Attack.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811203136.7A CN109359469A (en) | 2018-10-16 | 2018-10-16 | An information security risk assessment method for industrial control systems |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811203136.7A CN109359469A (en) | 2018-10-16 | 2018-10-16 | An information security risk assessment method for industrial control systems |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109359469A true CN109359469A (en) | 2019-02-19 |
Family
ID=65349182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811203136.7A Pending CN109359469A (en) | 2018-10-16 | 2018-10-16 | An information security risk assessment method for industrial control systems |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109359469A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059887A (en) * | 2019-04-25 | 2019-07-26 | 湖南大学 | BP neural network Risk Identification Method and system based on self-adapted genetic algorithm |
| CN110489972A (en) * | 2019-06-26 | 2019-11-22 | 中电万维信息技术有限责任公司 | The safety evaluation method and relevant device of electronic government affairs system |
| CN110703712A (en) * | 2019-10-25 | 2020-01-17 | 国家工业信息安全发展研究中心 | An industrial control system information security attack risk assessment method and system |
| CN110889587A (en) * | 2019-10-18 | 2020-03-17 | 国家电网有限公司 | Risk assessment method for distribution network lines |
| CN112291239A (en) * | 2020-10-29 | 2021-01-29 | 东北大学 | Network physical model facing SCADA system and intrusion detection method thereof |
| CN112330082A (en) * | 2020-08-13 | 2021-02-05 | 青岛科技大学 | Intelligent quantitative risk assessment method based on dynamic mechanism model |
| CN113159615A (en) * | 2021-05-10 | 2021-07-23 | 麦荣章 | Intelligent information security risk measuring system and method for industrial control system |
| CN113705098A (en) * | 2021-08-30 | 2021-11-26 | 国网江苏省电力有限公司营销服务中心 | Air duct heater modeling method based on PCA and GA-BP network |
| CN114418409A (en) * | 2022-01-21 | 2022-04-29 | 广东电网有限责任公司 | Equipment safety risk assessment method and device based on multiple neural networks |
| CN114493349A (en) * | 2022-02-16 | 2022-05-13 | 河海大学 | Case quality and effectiveness evaluation method and system based on PCA-BP-GA |
| CN114723960A (en) * | 2022-04-02 | 2022-07-08 | 湖南三湘银行股份有限公司 | Additional verification method and system for enhancing bank account security |
| CN116090839A (en) * | 2023-04-07 | 2023-05-09 | 水利部交通运输部国家能源局南京水利科学研究院 | Method and system for multiple risk analysis and assessment of water resource coupling system |
| CN116896452A (en) * | 2023-06-05 | 2023-10-17 | 云念软件(广东)有限公司 | Computer network information security management method based on data processing |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971162A (en) * | 2014-04-04 | 2014-08-06 | 华南理工大学 | Method for improving BP (back propagation) neutral network and based on genetic algorithm |
| CN105718876A (en) * | 2016-01-18 | 2016-06-29 | 上海交通大学 | Evaluation method of health states of ball screw |
| CN106130986A (en) * | 2016-06-30 | 2016-11-16 | 湘潭大学 | A kind of wind energy turbine set active safety defence method based on automated decision-making |
| CN106815652A (en) * | 2016-12-16 | 2017-06-09 | 国家电网公司 | A kind of distribution network reliability Forecasting Methodology based on big data correlation analysis |
| CN107316099A (en) * | 2017-05-22 | 2017-11-03 | 沈阳理工大学 | Ammunition Storage Reliability Forecasting Methodology based on particle group optimizing BP neural network |
| CN108400895A (en) * | 2018-03-19 | 2018-08-14 | 西北大学 | One kind being based on the improved BP neural network safety situation evaluation algorithm of genetic algorithm |
| CN108460461A (en) * | 2018-02-06 | 2018-08-28 | 吉林大学 | Mars earth shear parameters prediction technique based on GA-BP neural networks |
-
2018
- 2018-10-16 CN CN201811203136.7A patent/CN109359469A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971162A (en) * | 2014-04-04 | 2014-08-06 | 华南理工大学 | Method for improving BP (back propagation) neutral network and based on genetic algorithm |
| CN105718876A (en) * | 2016-01-18 | 2016-06-29 | 上海交通大学 | Evaluation method of health states of ball screw |
| CN106130986A (en) * | 2016-06-30 | 2016-11-16 | 湘潭大学 | A kind of wind energy turbine set active safety defence method based on automated decision-making |
| CN106815652A (en) * | 2016-12-16 | 2017-06-09 | 国家电网公司 | A kind of distribution network reliability Forecasting Methodology based on big data correlation analysis |
| CN107316099A (en) * | 2017-05-22 | 2017-11-03 | 沈阳理工大学 | Ammunition Storage Reliability Forecasting Methodology based on particle group optimizing BP neural network |
| CN108460461A (en) * | 2018-02-06 | 2018-08-28 | 吉林大学 | Mars earth shear parameters prediction technique based on GA-BP neural networks |
| CN108400895A (en) * | 2018-03-19 | 2018-08-14 | 西北大学 | One kind being based on the improved BP neural network safety situation evaluation algorithm of genetic algorithm |
Non-Patent Citations (3)
| Title |
|---|
| JOSÉ MANUELBERNAL DE LÁZARO 等: "Optimizing kernel methods to reduce dimensionality in fault diagnosis of industrial systems", 《COMPUTERS & INDUSTRIAL ENGINEERING》 * |
| 刘浩然 等: "一种基于改进遗传算法的神经网络优化算法研究", 《仪器仪表学报》 * |
| 李静 等: "制造业上市公司信息风险评估研究", 《武汉理工大学学报（信息与管理工程版）》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059887A (en) * | 2019-04-25 | 2019-07-26 | 湖南大学 | BP neural network Risk Identification Method and system based on self-adapted genetic algorithm |
| CN110489972A (en) * | 2019-06-26 | 2019-11-22 | 中电万维信息技术有限责任公司 | The safety evaluation method and relevant device of electronic government affairs system |
| CN110889587A (en) * | 2019-10-18 | 2020-03-17 | 国家电网有限公司 | Risk assessment method for distribution network lines |
| CN110703712A (en) * | 2019-10-25 | 2020-01-17 | 国家工业信息安全发展研究中心 | An industrial control system information security attack risk assessment method and system |
| CN110703712B (en) * | 2019-10-25 | 2020-09-15 | 国家工业信息安全发展研究中心 | Industrial control system information security attack risk assessment method and system |
| CN112330082B (en) * | 2020-08-13 | 2023-08-15 | 青岛科技大学 | An Intelligent Quantitative Risk Assessment Method Based on Dynamic Mechanism Model |
| CN112330082A (en) * | 2020-08-13 | 2021-02-05 | 青岛科技大学 | Intelligent quantitative risk assessment method based on dynamic mechanism model |
| CN112291239A (en) * | 2020-10-29 | 2021-01-29 | 东北大学 | Network physical model facing SCADA system and intrusion detection method thereof |
| CN113159615A (en) * | 2021-05-10 | 2021-07-23 | 麦荣章 | Intelligent information security risk measuring system and method for industrial control system |
| CN113159615B (en) * | 2021-05-10 | 2024-09-17 | 麦荣章 | An intelligent determination system and method for information security risk of industrial control systems |
| CN113705098A (en) * | 2021-08-30 | 2021-11-26 | 国网江苏省电力有限公司营销服务中心 | Air duct heater modeling method based on PCA and GA-BP network |
| CN114418409A (en) * | 2022-01-21 | 2022-04-29 | 广东电网有限责任公司 | Equipment safety risk assessment method and device based on multiple neural networks |
| CN114493349A (en) * | 2022-02-16 | 2022-05-13 | 河海大学 | Case quality and effectiveness evaluation method and system based on PCA-BP-GA |
| CN114723960A (en) * | 2022-04-02 | 2022-07-08 | 湖南三湘银行股份有限公司 | Additional verification method and system for enhancing bank account security |
| CN116090839A (en) * | 2023-04-07 | 2023-05-09 | 水利部交通运输部国家能源局南京水利科学研究院 | Method and system for multiple risk analysis and assessment of water resource coupling system |
| CN116896452A (en) * | 2023-06-05 | 2023-10-17 | 云念软件(广东)有限公司 | Computer network information security management method based on data processing |
| CN116896452B (en) * | 2023-06-05 | 2024-01-26 | 云念软件(广东)有限公司 | Computer network information security management method and system based on data processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359469A (en) | An information security risk assessment method for industrial control systems | |
| CN111966698B (en) | A blockchain-based trusted federated learning method, system, device and medium | |
| CN112460495B (en) | Monitoring point layout method and system for leakage monitoring positioning | |
| CN111931242A (en) | Data sharing method, computer equipment applying same and readable storage medium | |
| CN108718310A (en) | Multi-level attack signatures generation based on deep learning and malicious act recognition methods | |
| CN108683664B (en) | A network risk analysis and optimal active defense method based on a multi-level game model | |
| CN107273974B (en) | Method and system for constructing safety emergency disposal evaluation system | |
| CN108833416A (en) | A SCADA system information security risk assessment method and system | |
| Shirk et al. | Simulating pattern‐process relationships to validate landscape genetic models | |
| Donyaii et al. | Water reservoir multiobjective optimal operation using grey wolf optimizer | |
| CN112700326A (en) | Credit default prediction method for optimizing BP neural network based on Grey wolf algorithm | |
| CN110941902B (en) | Lightning stroke fault early warning method and system for power transmission line | |
| CN108337223A (en) | A kind of appraisal procedure of network attack | |
| CN117407800A (en) | A social media robot detection method and system based on random forest and XGBoost model | |
| Sbarufatti | Optimization of an artificial neural network for fatigue damage identification using analysis of variance | |
| Turner et al. | Adaptive decision rules for the acquisition of nature reserves | |
| Goel | ANN‐Based Approach for Predicting Rating Curve of an Indian River | |
| CN114547966A (en) | Neural network accelerator fault vulnerability assessment method based on hardware characteristic information | |
| Hart et al. | Accuracy and power analysis of social networks built from count data | |
| CN118827214A (en) | A multi-stage network defense method and system based on signal game | |
| Reddy et al. | An optimal neural network model for software effort estimation | |
| CN111292062A (en) | Crowdsourcing garbage worker detection method and system based on network embedding and storage medium | |
| CN116260647A (en) | Bidirectional Generative Adversarial Network Steam Turbine Network Intrusion Detection Method Based on Two-sided Features | |
| CN115174173B (en) | Global security game decision method of industrial information physical system in cloud environment | |
| CN115936831A (en) | Community risk conduction prediction method and system based on large-scale industrial and commercial graph network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190219 |