CN114021148B - System for predicting industrial control network bugs based on Summary word segmentation characteristics - Google Patents

Abstract

The invention relates to a system for predicting industrial control network bugs based on Summary participle characteristics,step S400 is realized, and a text sequence of each sample vulnerability id in the corresponding Summary is obtained; step S401, for Str_eProcessing to obtain corresponding word segmentation set A_eStep S402, when e =1, according to A_eDetermining the number of participles Str_eCharacteristic weight w of_e(ii) a Step S403, when e>At 1 time, Str is compared_e‑1And Str_eIf they are completely the same, w is set_e=w_e‑1If not identical, the part word set A is divided_eAnd a participle set A_e‑1Performing set difference set operation to obtain A_eRelative to A_e‑1Difference set fractional word number A_e‑A_e‑1And A is_e‑1Relative to A_eDifference set fractional word number A_e‑1‑A_e1Set up w_e=[(A_e‑A_e‑1）/(A_e‑1‑A_e1)]*w_e‑1(ii) a Step S404, determining each Str_eCorresponding Summary characteristic parameter values; s405, training to obtain an industrial control network vulnerability prediction model, and predicting the industrial control network vulnerability outbreak probability.

Description

System for predicting industrial control network bugs based on Summary word segmentation characteristics

Technical Field

The invention relates to the technical field of computers, in particular to a system for predicting industrial control network bugs based on Summary word segmentation characteristics.

Background

With the accelerated fusion of new-generation information technologies such as cloud computing, big data, artificial intelligence, internet of things and the like and manufacturing technologies, industrial control systems are independently opened from original closed, interconnected from a single machine and intelligentized from automation. When industrial enterprises obtain great development kinetic energy, a great deal of potential safety hazards also appear, and from Stuxnet viruses of iran nuclear plants in 2010 to Havex viruses in europe in the year 2014, network (hereinafter referred to as industrial control network) attacks of industrial control systems are more and more severe, and the industrial control systems are urgently required to obtain safety protection.

The system bugs of the industrial control system are important factors influencing the safety of the industrial control network, the bugs of the industrial control network cannot be repaired in time like an IT system, and a large number of bugs exist for a long time. Therefore, if the situation of vulnerability outbreak of the industrial control network cannot be predicted in time, and corresponding defense measures are taken, the safety of the industrial control network cannot be ensured. Therefore, how to accurately and efficiently predict the vulnerability outbreak situation of the industrial control network becomes a technical problem to be solved urgently.

Disclosure of Invention

The invention aims to provide a system for predicting the industrial control network vulnerability based on Summary word segmentation characteristics, which can quickly and accurately predict the explosion probability of the industrial control network vulnerability, thereby realizing that corresponding defense measures are taken based on the explosion probability of the industrial control network vulnerability and improving the safety of the industrial control network.

According to one aspect of the invention, a system for predicting industrial control network bugs based on Summary participle features is provided,

the system comprises a processor, a database and a storage medium storing a computer program, wherein the processor is in communication connection with the database, an internet vulnerability characteristic parameter list and an industrial control network vulnerability characteristic parameter list corresponding to all internet vulnerability ids are stored in the database, and the internet vulnerability characteristic parameters corresponding to the internet vulnerability ids comprise Summary; the computer program stored in the storage medium comprises a fourth computer program that, when executed by the processor, performs the steps of:

step S400, obtaining a text sequence { Str of each sample vulnerability id in corresponding Summary from the database₁,Str₂,…}，Str_eThe value range of e is 1 to infinity for the Summary text corresponding to the e-th updating period;

step S401, for Str_ePerforming word segmentation processing, and stopping words by using a preset stopping word bank to obtain Str_eCorresponding participle set A_e;

Step S402, when e =1, according to A_eDetermining the number of participles Str_eCharacteristic weight w of_e；

Step S403, when e>At 1 time, Str is compared_e-1And Str_eIf the text information of (1) is completely consistent with the text information of (1), setting w_e=w_e-1If Str_e-1And Str_eIf the text information is not completely consistent, the word set A is divided_eAnd a participle set A_e-1Performing set difference set operation to obtain A_eRelative to A_e-1Difference set fractional word number A_e- A_e-1And A is_e-1Relative to A_eDifference set fractional word number A_e-1-A_e1Set up w_e=[( A_e- A_e-1）/(A_e-1-A_e1) ]* w_e-1；

Step S404, based on each Str_eCharacteristic weight w of_eAnd Str_eDetermining each Str_eCorresponding Summary characteristic parameter value PCS_e=w_e*g(Str_e) Wherein, g (Str)_e) Is based on Str_eDetermining the original characteristic parameter value;

s405, constructing a model input vector based on the Summary characteristic parameter values corresponding to the sample vulnerability ids, training to obtain an industrial control network vulnerability prediction model, and predicting the industrial control network vulnerability outbreak probability based on the industrial control network vulnerability prediction model.

Compared with the prior art, the invention has obvious advantages and beneficial effects. By means of the technical scheme, the system for predicting the industrial control network vulnerability based on the Summary word segmentation characteristics can achieve considerable technical progress and practicability, has industrial wide utilization value and at least has the following advantages:

the system for predicting the industrial control network vulnerability based on the Summary participle characteristics can adjust the Summary characteristic weight according to the participle change relation of the Summary text in continuous periods, and improves the accuracy and the efficiency of obtaining Summary characteristic parameter values, so that the accuracy and the efficiency of training an industrial control network vulnerability prediction model are improved, and the accuracy and the efficiency of predicting the industrial control network vulnerability outbreak probability are improved. Reasonable defense measures are set based on the method, and the safety and the stability of the industrial control network are improved. The system is particularly suitable for application scenes with high Summary update frequency, namely application scenes with the Summary update frequency higher than a preset update frequency threshold.

The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.

Drawings

Fig. 1 is a schematic diagram of a system framework for predicting an industrial control network vulnerability according to an embodiment of the present invention;

fig. 2 is a flowchart of predicting an industrial control network vulnerability based on the internet and industrial control network vulnerability parameters according to an embodiment of the present invention;

fig. 3 is a flowchart of predicting an industrial control network vulnerability based on a correction parameter according to a second embodiment of the present invention;

fig. 4 is a flowchart of predicting an industrial control network vulnerability based on Summary length features according to a third embodiment of the present invention;

fig. 5 is a flowchart of predicting an industrial control network vulnerability based on Summary participle features according to the fourth embodiment of the present invention;

fig. 6 is a flowchart of predicting an industrial control network vulnerability based on bitmap according to a fifth embodiment of the present invention;

fig. 7 is a flowchart of predicting an industrial control network vulnerability based on an N-gram according to a sixth embodiment of the present invention.

Detailed Description

To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments and effects thereof will be made with reference to the accompanying drawings.

The industrial control network is an enterprise intranet, and is communicated with the Internet through a gateway, and a plurality of single-chip microcomputers, DSPs, industrial personal computers, sensors and the like are connected in the industrial control network. The same vulnerability may be exposed on the internet or on the industrial control network. Each vulnerability (CVE) has a corresponding vulnerability id (which may be a unique identifier labeled for each vulnerability by the international standards organization) and characteristic parameters. The vulnerability characteristic parameters comprise Internet vulnerability characteristic parameters crawled from the Internet and industrial control network vulnerability characteristic parameters crawled from an industrial control network. As an example, the internet Vulnerability feature parameters may specifically include a CVSS value set by a Common Vulnerability Scoring System (CVSS for short) for each Vulnerability id, a summery (Vulnerability description text) parameter, a CVSS parameter, a CWE (Common weak Enumeration) parameter, a product group parameter, a reference website domain name parameter, and other customized internet parameters, and the summery parameters may specifically include a summery text length, a summery word segmentation feature, and the like. The industrial control network vulnerability characteristic parameters comprise gateway parameters, internal state parameters of the industrial control network and the like. Each internet vulnerability characteristic parameter and each industrial control network vulnerability characteristic parameter correspond to an own updating period, and huge differences may exist between the updating periods of the parameters.

The embodiment of the invention provides a system for predicting industrial control network vulnerabilities, which comprises a processor, a database and a storage medium stored with a computer program, wherein the processor is in communication connection with the database, as shown in fig. 1. Those skilled in the art will appreciate that the processor is disposed on a server, and the server and the database are not particularly limited to a hardware device and/or a software device, but may be a server cluster, a storage cluster, and the like. It will be appreciated that any computing device or combination of computing devices capable of data processing may be provided with the server and any storage device or combination of storage devices capable of data storage may be considered the database. The server and the database may be separate devices or may share one or more separate devices.

The database stores an internet vulnerability characteristic parameter list P = { P } corresponding to all internet vulnerability ids₁，P₂,…P_MAn update period list TP of the internet vulnerability characteristic parameters = { TP = }₁，TP₂，…TP_MAnd a vulnerability characteristic parameter list Q = { Q) of the industrial control network₁，Q₂,…Q_NAnd an industrial control network vulnerability characteristic parameter update period list TQ = { TQ }₁，TQ₂，…TQ_N}。P_mIs the mth internet vulnerability characteristic parameter, TP_mIs P_mThe value range of M is 1 to M, and M is the quantity of the internet vulnerability characteristic parameters. Q_nTQ being the nth industrial control network vulnerability characteristic parameter_nIs Q_nThe value range of N is 1 to N, and N is the quantity of vulnerability characteristic parameters of the industrial control network.

The internet vulnerability characteristic parameter list specifically comprises at least one of a CVSS value, a CVSS parameter, a CWE parameter, a product group parameter, a reference website domain name parameter, a summary parameter and the like. And the internet vulnerability characteristic parameter list is updated correspondingly according to the updating period corresponding to each internet vulnerability characteristic parameter. The industrial control network vulnerability characteristic parameter list specifically comprises at least one of gateway parameters, internal state parameters of the industrial control network and the like.

And the industrial control network vulnerability characteristic parameters are correspondingly updated according to the updating period of each industrial control network vulnerability characteristic parameter. It should be noted that the internet vulnerability characteristic parameters are updated slowly, and the industrial control network vulnerability characteristic parameters can be monitored and obtained through the inside of the industrial control network, so that the updating frequency is high, and the accuracy can be up to the hour level or even the minute level. Therefore, the updating period of the internet vulnerability characteristic parameters is far longer than that of the industrial control network vulnerability characteristic parameters, and can be specifically set to max (TP)_m)/min(TQ_n)>D1, wherein D1 is a preset first threshold value, and D1 is set according to a specific application scene. For example, the value range of D1 is set to [10,100 ]]Preferably, D1= 20. Although the industrial control network and the internet are isolated through the gateway, the outbreak trend of the vulnerability on the internet and the outbreak trend of the industrial control network are consistent, and more vulnerability characteristic parameters can be crawled on the internet, so that the outbreak probability of the vulnerability on the industrial control network can be predicted based on the industrial control network vulnerability characteristic parameters and the internet vulnerability characteristic parameters by combining an artificial intelligence training industrial control network vulnerability prediction model.

As an example, the processor when processing the computer program implements the following steps:

step S1, acquiring vulnerability characteristic vectors corresponding to vulnerability ids of each sample from the Internet vulnerability characteristic parameter list and the industrial control network vulnerability characteristic parameter list based on a preset sample vulnerability id set, and constructing a training parameter set;

step S2, training according to the training parameter set to obtain an industrial control network vulnerability prediction model;

and step S3, predicting the explosion probability of the vulnerability id to be tested on the industrial control network based on the industrial control network vulnerability prediction model.

It can be understood that, since the probability of vulnerability outbreak is predicted by using historical data, the sample vulnerability id set may be a part of vulnerability ids in the current vulnerability id set, or may be all vulnerability ids, and is set according to specific requirements.

Because various internet vulnerability characteristic parameters and industrial control network vulnerability characteristic parameters exist and the updating periods are different, different vulnerability characteristic parameters can be selected, and different industrial control network vulnerability prediction models can be obtained through training in different processing modes. The detailed description will be described in detail below by way of a plurality of examples, and the technical contents of the respective examples may be cited as each other unless otherwise specified.

The first embodiment,

The computer program stored in the storage medium includes a first computer program that, when executed by the processor, implements the steps of:

step S101, obtaining a training period T of a training data set₀=LCM（TP_m) LCM is the function of solving the least common multiple.

Due to different P_mAnd Q_nThe update periods of the TP-based model are different, and if the sliding window is directly used for selecting the training parameters, many parameters are not changed within a certain time, which wastes computing resources and has little significance for model training, so that the TP is selected in the embodiment_mThe small common multiple of (c) is used as the training period. It should be noted that, the updating period of the characteristic parameters of the internet vulnerability is far awayThe time window is selected only by considering the updating period of the internet vulnerability characteristic parameters, so that all the internet vulnerability characteristic parameters and the industrial control network vulnerability characteristic parameters can be acquired by each sample vulnerability id, the waste of calculation power is avoided, and the efficiency of model training is improved.

S102, obtaining T before the current moment and corresponding to each sample vulnerability id from the database₀Inner P_mList of parameter values, Q_nThe parameter value list and the industrial control network vulnerability outbreak probability truth value are obtained;

the actual explosion probability value of the industrial control network vulnerability refers to the actual explosion probability of the industrial control network vulnerability corresponding to the sample prediction moment, the actual explosion probability of the industrial control network vulnerability is also a parameter updated in the corresponding updating period, and the actual explosion probability of the industrial control network vulnerability is obtained by dividing the number of the industrial control network host equipment reporting the explosion of the vulnerability by the number of all monitored industrial control network host equipment in the updating period of the industrial control network vulnerability explosion probability.

Step S103, P based on vulnerability id of each sample_mDetermining P corresponding to sample vulnerability id by parameter value list_mTraining parameter value PC_mQ based on per sample vulnerability id_nDetermining Q corresponding to sample vulnerability id by using parameter value list_nTraining parameter value QC of_nBased on PC_mAnd QC_nGenerating a model input vector of each sample vulnerability id;

step S104, training according to all sample vulnerability id model input vectors and industrial control network vulnerability outbreak probability truth values to obtain an industrial control network vulnerability prediction model:

f(x)=a₁*x₁+a₂*x₂+…a_M+N*x_M+N，

wherein x is_iP corresponding to sample vulnerability id_mTraining parameter value or Q of_nTraining parameter values of a_iIs x_iThe value range of i is 1 to M + N;

and S105, predicting the explosion probability of the industrial control network vulnerability based on the industrial control network vulnerability prediction model.

As an example, the step S104 includes:

and S114, inputting all sample vulnerability id model input vectors into a preset industrial control network vulnerability prediction model to obtain a sample industrial control network vulnerability outbreak probability prediction value.

Step S124, the weight coefficient is adjusted according to the sample industrial control network vulnerability outbreak probability predicted value and the true value, and the industrial control network vulnerability prediction model is obtained through training.

As an example, in the step S105, a training period T corresponding to the training data set is preferably adopted₀In the same period, the same input vector construction strategy from the step S102 to the step S104 is adopted to predict the vulnerability outbreak probability of the industrial control network, and the prediction accuracy is high.

As another example, the selected time period when the industrial control network vulnerability prediction model is trained is much longer than the period of the characteristic parameters of the industrial control network vulnerability, but because the period of the characteristic parameters of the industrial control network vulnerability is broken and the updating frequency is high, when at least one characteristic parameter of the industrial control network vulnerability is updated, the industrial control network vulnerability can be predicted, the prediction sensitivity is high, and the predictability of the newly-outbreak vulnerability is very strong. Specifically, the step S105 includes:

step S134, obtaining the prediction period T₁=min(TQ_n)；

Step S144, every interval T₁Collecting P of current moment corresponding to vulnerability id to be tested_mValue of parameter or Q_nConstructing an input vector corresponding to the id of the vulnerability to be tested;

step S154, inputting the input vector corresponding to the loophole id to be detected into the industrial control network loophole prediction model to obtain T after the current moment of the loophole id to be detected₁And (5) the vulnerability outbreak probability of the industrial control network at the moment.

As a preferred example, in step S103, the distance T before the current time corresponding to each sample vulnerability id is T₀Inner P_mIs listed as { PC_m1,PC_m2,…PC_mAWhere, PC_maIs P_mAt T₀The value of the a-th parameter in (a),a ranges from 1 to A, A is P_mBefore the current time T₀Internally collected P_mTotal number of parameter values, a = T₀/TP_mP based on per sample vulnerability id_mDetermining P corresponding to sample vulnerability id by parameter value list_mTraining parameter value PC_mThe method comprises the following steps:

step S113, determining P based on the following equation_mTraining parameter value PC_m：

。

Due to different parameter updating periods, most of the internet vulnerability characteristic parameters and industrial control network vulnerability characteristic parameters can obtain a plurality of characteristic parameters in a training period, and therefore reasonable characteristic parameter values need to be determined based on the plurality of characteristic parameters to construct model input. As a preferred example, in step S103, the distance T before the current time corresponding to each sample vulnerability id is T₀Inner Q_nIs listed as { QC_n1,QC_n2,…QC_nB}, QC_nbIs Q_nBefore the current time T₀The value range of the B parameter value in the (B) is 1 to B, and B is Q_nBefore the current time T₀Internally collected Q_nTotal number of parameter values, B = T₀/ TQ_nQ based on per sample vulnerability id_nDetermining Q corresponding to sample vulnerability id by using parameter value list_nTraining parameter value QC of_nThe method comprises the following steps:

step S123, determining Q based on the following equation_nTraining parameter value QC of_n：

。

As time goes on, a new bug may be added, and the bug characteristic parameters and the bug characteristic parameter update period may also change, so that in order to further improve the accuracy of the industrial control network bug prediction model, the processor implements the following steps when executing the first computer program:

step S100, every interval T₀And re-executing the step S101 to the step S104 to update the industrial control network vulnerability prediction model.

In the first embodiment, the internet vulnerability characteristic parameters and the industrial control network vulnerability characteristic parameters are obtained by setting a reasonable training period of a training data set, corresponding parameter values are respectively determined based on the internet vulnerability characteristic parameters and the industrial control network vulnerability characteristic parameters in the training period, then the corresponding parameter values are converted into input vectors, and an industrial control network vulnerability prediction model is obtained through training. The method has the advantages that the vulnerability outbreak probability of the industrial control network can be rapidly and accurately predicted based on the internet vulnerability characteristic parameters and the industrial control network vulnerability characteristic parameters with multiple dimensions, reasonable defense measures are set based on the vulnerability outbreak probability, and the safety and the stability of the industrial control network are improved. The method and the device are particularly suitable for application scenes capable of simultaneously obtaining the internet vulnerability characteristic parameters and the industrial control network vulnerability characteristic parameters.

Example II,

It should be noted that the internet vulnerability characteristic parameters are many and easy to obtain, but in some application scenarios, the internet vulnerability characteristic parameters are limited by various factors such as the scale of the industrial control network, and sufficient industrial control network vulnerability characteristic parameters may not be obtained to train the industrial control network vulnerability prediction model. However, because the trend of the same vulnerability outbreak in the industrial control network is consistent with the overall trend of the same vulnerability outbreak in the internet and has relevance, the vulnerability outbreak probability of the industrial control network can be predicted based on the incidence relation between the industrial control network and the internet vulnerability outbreak and by combining with the internet vulnerability characteristic parameters.

Specifically, the computer program stored in the storage medium includes a second computer program, and when the processor executes the second computer program, the following steps are implemented:

step S201, obtaining P corresponding to each sample vulnerability id in a preset training period from the database_mThe method comprises the steps of parameter value list, internet vulnerability actual outbreak probability list, industrial control network vulnerability actual outbreak probability list and industrial control network vulnerability outbreak probability truth value.

The preset training period can be set according to specific training requirements, and can also be determined directly based on a mode of obtaining the least common multiple of the update period of the internet vulnerability characteristic parameters in the embodiment. The actual outbreak probability of the internet vulnerability is also a parameter updated in the corresponding updating period, and is obtained by dividing the number of the internet host devices reporting the outbreak of the vulnerability by the number of all the monitored internet host devices in the updating period of the outbreak probability of the internet vulnerability. The specific algorithm for obtaining the true value of the industrial control network vulnerability outbreak probability and the actual outbreak probability of the industrial control network vulnerability is described in detail in the first embodiment, and is not described herein again.

Step S202, determining a correction parameter P corresponding to each sample vulnerability id based on an Internet vulnerability actual outbreak probability list and an industrial control network vulnerability actual outbreak probability list_CVEBased on P corresponding to each sample vulnerability id_mDetermines the corresponding training parameter value PC_mBased on PC_mAnd generating a model input vector of each sample vulnerability id.

Note that, the correction parameter P_CVEThe method is used for expressing the incidence relation between the internet actual vulnerability outbreak probability and the industrial control network actual vulnerability outbreak probability value of each sample vulnerability id, and each sample vulnerability id has a corresponding correction parameter P_CVEIs a dynamically changing value based on each vulnerability id.

Step S203, correcting parameters P corresponding to all sample loopholes id_CVETraining the model input vector and the industrial control network vulnerability outbreak probability truth value to obtain an industrial control network vulnerability prediction model:

f(x)=b₀*P_CVE+b₁*x₁+b₂*x₂+…b_M *x_M;

wherein x is_jP corresponding to sample vulnerability id_mTraining parameter values of b_jIs x_jThe value of j ranges from 1 to M.

It should be noted that the model constructs an input vector based on the characteristic parameters of the internet vulnerability, and represents the actual vulnerability outbreak probability of the internet and the actual industrial control network based on the corresponding characteristic parametersCorrection parameter P of incidence relation between probability values of interpeak vulnerability outbreak_CVEMeanwhile, the probability of vulnerability outbreak of the industrial control network is predicted based on the characteristic parameters of the internet vulnerabilities as model input.

And S204, predicting the explosion probability of the industrial control network vulnerability based on the industrial control network vulnerability prediction model.

It can be understood that after the vulnerability prediction model is trained, the probability of vulnerability outbreak in the industrial control network can be predicted based on the input parameters corresponding to the vulnerability at any time.

Based on the correction parameter P_CVEAnd predicting the vulnerability outbreak probability of the industrial control network by using the internet characteristic parameters. Therefore, how to determine the reasonably accurate correction parameter P in the model training process_CVEThis is particularly important. As an example, in step S202, a correction parameter P corresponding to each sample vulnerability id is determined based on the internet vulnerability actual outbreak probability list and the industrial control network vulnerability actual outbreak probability list_CVEThe method comprises the following steps:

step S212, obtaining an Internet and industrial control network vulnerability outbreak association parameter list { R ] according to an Internet vulnerability actual outbreak probability list and an industrial control network vulnerability actual outbreak probability list corresponding to each sample vulnerability id in a preset training period₁，R₂，…R_C},R_cThe value range of C is 1 to C for the C-th associated parameter, C is the total number of the associated parameters obtained by the sample vulnerability id in the preset training period, R_c=CH_c1/CH_c2，CH_c1Is the actual outbreak probability value, CH, of the internet vulnerability at the c moment_c2And the actual explosion probability of the industrial control network vulnerability at the c-th moment.

Step S222, according to { R₁，R₂，…R_CDetermining a correction parameter P corresponding to a sample vulnerability id_CVE。

As an example, the step S222 includes:

step S232, obtaining { R₁，R₂，…R_CMean value of R_AVGAccording to R_AVGAnd { R₁，R₂，…R_CAcquiring a first variation parameter SR 1:

；

step S242, if SR1 is greater than or equal to the preset second threshold D2, { R [ ] is obtained₁，R₂，…R_CMaximum value R of }_maxSetting up P_CVE=R_maxOtherwise, set P_CVE=R_AVG。

It should be noted that if SR1 is greater than or equal to the preset second threshold D2, it indicates that there is a sudden burst period in the current training period, and therefore { R is selected₁，R₂，…R_CThe maximum value of the correction parameter P_CVEAnd is more accurate. If SR1 is less than the second threshold D2, it indicates that the vulnerability is relatively stable in the current training period, so R is selected₁，R₂，…R_CAs a correction parameter P_CVEAnd is more accurate. By reasonably selecting accurate correction parameter P_CVEThe accuracy of the industrial control network vulnerability prediction model can be improved, the model has high sensitivity to emerging vulnerability prediction, and the method is particularly suitable for application scenes of emerging vulnerability prediction.

To further improve the selection of the correction parameter P_CVEIf SR1 is smaller than D2 in step S242, the following steps may be further performed:

step S252, { R }₁，R₂，…R_CMinimum value R of }_minAccording to R_min、R_AVG、R_maxAcquiring a second variation parameter SR 2:

；

step S262, if SR2 is greater than or equal to 1, setting P_CVE=R_minOtherwise, set P_CVE=R_max。

When SR2 is 1 or more, R will be described_minThe influence of (a) is larger,thus, P is preferred_CVE=R_minThis situation is typically applicable in scenarios where an existing vulnerability is suddenly fixed, in which case R is_minIs more influential, P is selected_CVE=R_minThe model accuracy can be improved. If SR2 is less than 1, then it indicates R_maxIs more influential, P is therefore preferred_CVE=R_maxTherefore, the model has strong sensitivity to the newly appeared vulnerability prediction, and is particularly suitable for application scenarios of the newly appeared vulnerability prediction.

As an example, in the step S202, P corresponding to each sample vulnerability id is used as a basis_mDetermines the corresponding training parameter value PC_mThe method comprises the following steps:

step S272, corresponding P of each sample vulnerability id_mDetermining the maximum value, the minimum value or the average value of all the parameters in the parameter value list as the corresponding training parameter value PC_m。

In the system of the second embodiment, through the internet vulnerability characteristic parameters and the correction parameter P representing the incidence relation between the internet actual vulnerability outbreak probability and the industrial control network actual vulnerability outbreak probability value_CVEAnd (4) constructing model input parameters, and training to obtain an industrial control network vulnerability prediction model. The method realizes the internet vulnerability characteristic parameters and the correction parameters P based on multiple dimensions_CVETherefore, the vulnerability outbreak probability of the industrial control network is rapidly and accurately predicted, reasonable defense measures are set based on the probability, and the safety and the stability of the industrial control network are improved. The second embodiment is particularly suitable for application scenarios in which vulnerability characteristic parameters of the industrial control network are not easy to obtain. Reasonable defense measures are set based on the method, and the safety and the stability of the industrial control network are improved.

The Summary parameter is the text description of the vulnerability by an authority, and can accurately and reliably reflect vulnerability characteristics, so that the characteristic parameter for predicting the industrial control network vulnerability can be constructed based on Summary. Summary is an unstructured parameter, so a feature parameter value needs to be constructed based on the text feature of Summary, for example, in the prior art, the length of Summary is directly based on the length of Summary, and the longer the length of Summary is, the vulnerability is shown to be damagedThe greater the sex, the greater the urgency of the need for treatment. However, since Summary is generally all Summary updated regularly by the authority, only Summary of vulnerability changed in a period will be changed, and Summary unchanged in other periods is kept consistent with Summary in the previous period when updated. For example, for a serious vulnerability outbreak three years ago, there is long text description information, but no other change occurs within three years, so the Summary description stays in the description state three years ago, and if only the feature parameter value is directly constructed from the Summary text, it is obviously most likely that the constructed Summary feature parameter value is inaccurate. Therefore, the corresponding feature weight value needs to be given according to the change of the Summary, so that the accuracy of building the Summary feature parameter is improved. Therefore, it is important to determine the feature weight value corresponding to each Summary, and the following detailed description is provided by some specific embodiments.

Example III,

The computer program stored in the storage medium comprises a third computer program that, when executed by the processor, performs the steps of:

step S300, obtaining a text sequence { Str of each sample vulnerability id in corresponding Summary from the database₁,Str₂,…}，Str_eThe value range of e is 1 to infinity for the Summary text corresponding to the e-th updating period.

Step S301, when e =1, according to Str_eLength of (1) determining Str_eCharacteristic weight w of_e。

Through step S301, can be for each Str_eAnd setting corresponding initial characteristic weight.

Step S302, when e>At 1 time, Str is compared_e-1And Str_eIf the text information of (2) is completely consistent, judging z x w_e-1Whether the weight is larger than a preset first characteristic weight threshold value w_eminIf greater than, set w_e=z*w_e-1Wherein z is a preset weight adjustment coefficient, 0<z<1, if z x w_e-1Is less than or equal to w_eminThen set w_e=w_eminIf Str_e-1And Str_eIf the text information of (1) is not consistent, according to Str_eLength of (1) determining Str_eCharacteristic weight w of_e。

It should be noted that when Str_e-1And Str_eWhen the text information is completely consistent, it means that Summary is not updated, so it needs to multiply z to reduce the corresponding feature weight. Preferably, z is set to 1/2 but some Summary have long-term non-update conditions and cannot be decreased without limit, so the first feature weight threshold w is set_eminWhen w is_eWhen the temperature is reduced to a certain degree, the minimum value is selected. When Str is formed_e-1And Str_eIf the text information of (2) is inconsistent, it indicates that Summary is changed, so it needs to be directly based on the current Str_eLength of (1) determining Str_eCharacteristic weight w of_e。

Step S303, based on each Str_eCharacteristic weight w of_eAnd Str_eDetermining each Str_eCorresponding Summary characteristic parameter value PCS_e=w_e*g(Str_e) Wherein, g (Str)_e) Is based on Str_eAnd determining the original characteristic parameter value.

In addition, g (Str)_e) The parameter value may be obtained directly based on an existing algorithm, that is, a corresponding parameter value is determined directly based on a text feature, and the existing algorithm is not described herein again. w is a_eThe method is determined based on the characteristic parameters of the Summary and the change of the Summary in continuous periods, so that the acquired Summary characteristic parameter values PCS are enabled to be_eMore accurate and reliable, thereby improving the accuracy of the model.

S304, constructing a model input vector based on the Summary characteristic parameter values corresponding to the sample vulnerability ids, training to obtain an industrial control network vulnerability prediction model, and predicting the industrial control network vulnerability outbreak probability based on the industrial control network vulnerability prediction model.

It can be understood that other required internet vulnerability characteristic parameters and industrial control network vulnerability characteristic parameters may be introduced when the input vector is constructed, and the specific parameter processing may be based on the methods described in the first embodiment and the second embodiment, or may adopt the existing data processing method, which is not described herein again.

As an example, in step S301 and step S302, according to Str_eLength of (1) determining Str_eCharacteristic weight w of_eThe method comprises the following steps:

step S311, Str_eLength L of_eAnd a preset first length threshold value L_minAnd a second length threshold L_maxComparison, first length threshold L_minLess than a second length threshold L_maxIf L is_e<L_minThen set w_e=w_eminIf L is_e>L_maxThen set w_e=w_emax，w_emaxIs a preset second feature weight threshold, the second feature weight threshold is greater than the first feature weight threshold, L_eIn [ L ]_min，L_max]Within the range, then set w_e=k₁*L_eWherein k is₁Is a preset first linear change coefficient.

Through step S311, Str can be based_eLength L of_eAn accurate and reliable initial feature weight is determined. Preferably, k is₁Is set as (w)_emax- w_emin）/ w_emax

As a preferred example, when e >1, before performing step S311, the method further includes:

step S310, determining w_e-1Whether or not based on w_e-1=z*w_e-2Set, if yes, and Str_e-1And Str_eIf the text information of (1) is not consistent, w is set_emin= w_e-1。

When w is_e-1=z*w_e-2Then, it is described that the Summary in the previous two periods has not changed, and the previous period has reduced the weight, and the current period has changed compared with the Summary in the previous period, so the weight of the current period must be greater than the weight of the previous period, at this time, w in the current period can be calculated_eminIs set as w_e-1The accuracy of obtaining the characteristic weight of the period is improved. It is understood that if not the case in step S310, then w_eminStill the original preset value.

As an example, in step S304, a model input vector is constructed based on the Summary feature parameter value corresponding to the sample vulnerability id, and the industrial control network vulnerability prediction model is obtained through training, which includes:

step S314, determining a model input vector of each sample vulnerability id according to the Summary characteristic parameter value corresponding to the sample vulnerability id, a preset internet vulnerability characteristic parameter and a preset industrial control network vulnerability characteristic parameter;

step S324, training based on model input vectors corresponding to sample vulnerability ids and the industrial control network vulnerability outbreak probability truth value to obtain the industrial control network vulnerability prediction model.

It can be understood that, after the model sample input is determined, the selected artificial intelligence model can be trained by obtaining the corresponding sample true value, the input parameter can be set to a preset training period, and the processing mode of the input parameter can be processed based on the processing mode in the first embodiment and the second embodiment, or can be processed by the existing processing mode, which is not described herein.

It should be noted that, the algorithm directly executed in step S301 after step S300 is executed is applicable to the vulnerability ids of the corresponding Summary text from the time e =1, but some vulnerability ids are newly added later, and a set of corresponding feature weight determination policy may also be set for such vulnerability ids, as an example, the step S300 further includes:

step S311, if { Str₁,Str₂… } preceding nr consecutive strs in sequence_eIs empty, Str_nr+1If not, Str is set_nr+1Characteristic weight w of_nr+1= w_emax，w_emaxFor a preset second feature weight threshold, then initializing e = nr +2, and performing step S302.

It should be noted that if { Str₁,Str₂… } preceding nr consecutive strs in sequence_eIs empty, Str_nr+1If not, it indicates that the corresponding bug id is a new bug id at nr +1, then Str_nr+1Characteristic weight w of_nr+1It is sufficient to directly set the maximum value second feature weight threshold,on the premise of ensuring the accuracy, the data processing amount can be reduced, and the data processing efficiency can be improved.

The third embodiment can adjust the feature weight of the Summary according to the text change and the length change of the Summary in the continuous period, the text change of the Summary is easy to judge, and the length parameter is easy to obtain, so that the accuracy and the obtaining efficiency of obtaining the Summary feature parameter value are improved, the accuracy and the training efficiency of training the industrial control network vulnerability prediction model are improved, and the accuracy and the prediction efficiency of predicting the industrial control network vulnerability outbreak probability are improved. Reasonable defense measures are set based on the method, and the safety and the stability of the industrial control network are improved.

Example four,

The fourth embodiment provides an application scenario more suitable for a high Summary update frequency, that is, the Summary update frequency exceeds a preset update frequency threshold.

The computer program stored in the storage medium comprises a fourth computer program that, when executed by the processor, performs the steps of:

step S400, obtaining a text sequence { Str of each sample vulnerability id in corresponding Summary from the database₁,Str₂,…}，Str_eThe value range of e is 1 to infinity for the Summary text corresponding to the e-th updating period.

Step S401, for Str_ePerforming word segmentation processing, and stopping words by using a preset stopping word bank to obtain Str_eCorresponding participle set A_e。

It should be noted that the preset deactivation word library may be a deactivation word library constructed based on technologies, and may be continuously changed according to application requirements. The industrial internet decommissioning word library described in the subsequent embodiment may also be used, and the industrial internet decommissioning word library may also be updated according to the updating method of the industrial internet decommissioning word library described in the sixth embodiment, which is not described herein again.

Step S402, when e =1, according to A_eDetermining the number of participles Str_eCharacteristic weight w of_e。

Through the process of the step S402, the process,may be based on A_eNumber of participles per Str_eAnd setting corresponding initial characteristic weight.

Step S403, when e>At 1 time, Str is compared_e-1And Str_eIf the text information of (1) is completely consistent with the text information of (1), setting w_e=w_e-1If Str_e-1And Str_eIf the text information is not completely consistent, the word segmentation set A is divided_eAnd a participle set A_e-1Performing set difference set operation to obtain A_eRelative to A_e-1Difference set fractional word number A_e- A_e-1And A is_e-1Relative to A_eDifference set fractional word number A_e-1-A_e1Set up w_e=[( A_e- A_e-1）/(A_e-1-A_e1) ]* w_e-1。

It should be noted that when Str_e-1And Str_eWhen the text information is completely consistent, it indicates that the Summary is not updated, and because the Summary update frequency is fast, w can be set directly_e=w_e-1. If Str_e-1And Str_eIf the text information is not completely consistent, the text information needs to be based on A_eAnd A_e-1The change relationship between the characteristic weight and the weight to determine the characteristic weight change coefficient [ (A)_e- A_e-1）/(A_e-1-A_e1) ]And is further based on [ (A)_e- A_e-1）/(A_e-1-A_e1) ]And the weight w of the previous cycle_e-1To determine w_e，A_e- A_e-1And A_e-1-A_e1In contrast, if A_e- A_e-1Greater than A_e-1-A_e1Description of A_eIn A_e-1Add more words on the basis of (A), if A_e- A_e-1Is less than A_e-1-A_e1Description of A_eIn A_e-1Reduce more words on the basis of (A), thus leading to (A)_eIn A_e-1When more words are added on the basis, the feature weight becomes larger, A_eIn A_e-1When more words are reduced on the basis, the characteristic weight is reduced, and the determined characteristic weight w is improved_eThe accuracy of (2).

Step S404, based on each Str_eCharacteristic weight w of_eAnd Str_eDetermining each Str_eCorresponding Summary characteristic parameter value PCS_e=w_e*g(Str_e) Wherein, g (Str)_e) Is based on Str_eAnd determining the original characteristic parameter value.

In addition, g (Str)_e) The parameter value may be obtained directly based on an existing algorithm, that is, a corresponding parameter value is determined directly based on a text feature, and the existing algorithm is not described herein again. w is a_eIs determined based on the characteristic parameters of the Summary and the change of the Summary in continuous periods, so that the acquired Summary characteristic parameter value PCS is enabled to be_eMore accurate and reliable, thereby improving the accuracy of the model.

S405, constructing a model input vector based on the Summary characteristic parameter values corresponding to the sample vulnerability ids, training to obtain an industrial control network vulnerability prediction model, and predicting the industrial control network vulnerability outbreak probability based on the industrial control network vulnerability prediction model.

It can be understood that other required internet vulnerability characteristic parameters and industrial control network vulnerability characteristic parameters may be introduced when the input vector is constructed, and the specific parameter processing may be based on the methods described in the first embodiment and the second embodiment, or may adopt the existing data processing method, which is not described herein again.

As an example, the step S402 includes:

step S412, A_eNumber of participles SA_eWith a predetermined first threshold value SU_minAnd a first threshold value SU_maxComparison, wherein SU_min<SU_maxIf SA_e< SU_minThen set w_e= ws_min，ws_minIs a preset third feature weight threshold if SA_e>SU_maxThen set w_e= ws_max，ws_maxIs a preset fourth characteristic weight threshold value, if the preset third characteristic weight threshold value is in [ SU ]_min，SU_max]Then set w_e=k₂*SA_eWherein k is₂Is a preset second linear change coefficient.

Preferably, ws_minSet to 0, ws_maxThe setting is 1, which facilitates the calculation.

Through step S412, can be based on A_eNumber of participles SA_eAn accurate and reliable initial feature weight is determined. Preferably, k is₂Is set to (ws)_max-ws_min）/ ws_max。

It should be noted that, the algorithm directly executing step S402 after step S401 is executed is applicable to the vulnerability ids of the corresponding Summary text from the time e =1, but some vulnerability ids are newly added later, and a set of corresponding feature weight determination policy may also be set for such vulnerability ids, as an example, step S401 further includes:

step 422, if { Str₁,Str₂… } consecutive first ns strs_eA of (A)_eIs empty, A_e+1If not, Str is set_ns+1Characteristic weight w of_ns+1= ws_max，ws_maxFor a preset third feature weight threshold, then initializing e = ns +2, and performing step S403.

It should be noted that if { Str₁,Str₂… } consecutive first ns strs_eA of (A)_eIs empty, A_e+1If not, it indicates that the corresponding bug id is the newly added bug id in ns +1, then Str_ns+1Characteristic weight w of_ns+1The maximum value third characteristic weight threshold value can be directly set, so that the data processing amount can be reduced and the data processing efficiency can be improved on the premise of ensuring the accuracy.

As an example, in step S405, a model input vector is constructed based on the Summary feature parameter value corresponding to the sample vulnerability id, and an industrial control network vulnerability prediction model is obtained through training, including:

step S415, determining a model input vector of each sample vulnerability id according to the Summary characteristic parameter value corresponding to the sample vulnerability id, a preset internet vulnerability characteristic parameter and a preset industrial control network vulnerability characteristic parameter;

and S425, training based on model input vectors corresponding to sample vulnerability ids and the true value of the vulnerability outbreak probability of the industrial control network to obtain the industrial control network vulnerability prediction model.

The fourth embodiment is particularly suitable for application scenarios with high Summary update frequency, that is, application scenarios with Summary update frequency higher than a preset update frequency threshold. The method has the advantages that the feature weight of the Summary can be adjusted according to the word segmentation change relation of the Summary text in the continuous period, and the accuracy and the efficiency of obtaining the Summary feature parameter values are improved, so that the accuracy and the efficiency of training the industrial control network vulnerability prediction model are improved, and the accuracy and the prediction efficiency of predicting the industrial control network vulnerability outbreak probability are improved. Reasonable defense measures are set based on the method, and the safety and the stability of the industrial control network are improved.

Example V,

The fifth embodiment is particularly suitable for application scenarios with low Summary update frequency, that is, application scenarios with Summary update frequency lower than a preset update frequency threshold.

The system also comprises a bitmap (bitmap) generated by changing the Summary text corresponding to each vulnerability id along with the updating period, and the bitmap is used for storage, so that the data storage space can be saved. If the text of the Summary in the current period is not changed relative to the text of the Summary in the previous period, the position of the current period in the corresponding period of the bitmap is set to be 0, otherwise, the position is set to be 1, B_eThe value corresponding to the bitmap in the e-th update period, B_eEqual to 0 or 1, e has a value of 1 to infinity.

The computer program stored in the storage medium includes a fifth computer program that, when executed by the processor, implements the steps of:

step S501, determining a Summary cycle detection window TK based on a preset training cycle, wherein TK = a Te, a is a positive integer larger than 1, and Te is a Summary update cycle;

it is understood that the period detection window TK comprises a bits, each bit corresponding to an update period. Preferably, a has a value of 8.

Step S502, with B_eAs the a-th bit information in the TK, the e-th cycle detection window information TK is obtained_eBased on B_eAnd TK_eBit change in (c), determining B_eCharacteristic weight w of_e。

In addition, the following formula B_eAs the a-th bit information in TK, i.e. B_eThe last bit of information in the TK. TK_eChange of position in (TK)_eThe variation of a bits in (1) corresponds to the variation of Summary of a consecutive cycles. For example, if all the a bits are 0, it indicates that the Summary does not change in a consecutive a cycles. As another example, B_eIs 1, description B_eThe corresponding Summary is changed from the Summary of the previous cycle. As another example, B_eIs 0, B_e-a1Is 1, B_e-a1And B_eAll the values in the interval are 0, B is indicated_eThe corresponding Summary continues for a1 cycles without change, and is therefore based on B_eAnd TK_eA bit change in (B) can be determined_eCharacteristic weight w of_e

Step S503, based on each B_eCharacteristic weight w of_eAnd Summary text Str_eDetermining a Summary characteristic parameter value PCS corresponding to each Summary text_e=w_e*g(Str_e) Wherein, g (Str)_e) Is based on Str_eAnd determining the original characteristic parameter value.

In addition, g (Str)_e) The parameter value may be obtained directly based on an existing algorithm, that is, a corresponding parameter value is determined directly based on a text feature, and the existing algorithm is not described herein again. w is a_eIs determined based on the characteristic parameters of the Summary and the change of the Summary in continuous periods, so that the acquired Summary characteristic parameter value PCS is enabled to be_eMore accurate and reliable, thereby improving the accuracy of the model.

Step S504, a model input vector is constructed based on the Summary characteristic parameter values corresponding to the sample vulnerability ids, an industrial control network vulnerability prediction model is obtained through training, and the industrial control network vulnerability outbreak probability is predicted based on the industrial control network vulnerability prediction model.

It can be understood that other required internet vulnerability characteristic parameters and industrial control network vulnerability characteristic parameters may be introduced when the input vector is constructed, and the specific parameter processing may be based on the methods described in the first embodiment and the second embodiment, or may adopt the existing data processing method, which is not described herein again.

As an example, in step S502, the base B is_eAnd TK_eBit change in (c), determining B_eCharacteristic weight w of_eThe method comprises the following steps:

step S512, judging B_eIf it is 1, then set w_e=wb_max，wb_maxIs a preset fifth feature weight threshold, otherwise, step S522 is executed;

step S522, TK is obtained_eIn and B_eThe most recent bit taking the value 1 and B_eNumber of bits of interval d, judgment (wb)_max- wb_min) Whether/d is less than a preset sixth characteristic weight threshold wb_minIf it is smaller than, set w_e= wb_minOtherwise set w_e=（wb_max- wb_min）/d，wb_min< wb_max。

Since the update frequency of Summary is low, when Summary is updated compared with Summary in the previous period, it should have high weight, and through steps S512-S522, it can be used for w that the current period changes compared with the previous period_eSet directly to wb_maxTherefore, the accuracy can be ensured, and the calculation amount can be reduced. It is understood that, if a more accurate result is required, the calculation may be specifically performed based on the sum length or the word segmentation result in the third embodiment and the fourth embodiment, and details are not described herein. When the Summary is not updated compared with the Summary of the previous period, determining corresponding weight based on the distance between the current period and the last updating period, and acquiring K based on the bitmap_eNeutral and B_eMost recent bit value 1 and B_eThe number d of the interval bits is small in calculation amount and high in calculation efficiency.

As an example, to further improve the quasi-determination of feature weight acquisition, wb may be dynamically adjusted based on the results of the last cycle detection window_maxAnd wb_minAfter step S522, the method further includes:

step S532, all w obtained based on the TK of the current Summary period detection window_eMax (w) of_e) And minimum value min (w)_e) Update wb_max= max(w_e) Update wb_min= min(w_e)。

In order to further improve the efficiency of acquiring the feature weight, the bit operation may be performed directly based on bitmap, and as an example, the step S502 includes:

step S542 and B_eAs the a-th bit information in the TK, obtaining the bitmap in the e-th period detection window_eInitializing WK as binary, corresponding initial decimal number of WK as 2^a-1;

Step S552, judging the current bitmap_eIs 0, if yes, go to step S562, if yes, go to step S572 if no, go to step S1;

step S562, the e-th periodic detection window is shifted to the right by one bit, and bitmap is updated_eWK is shifted right by one bit, and the process returns to step S552;

step S572, determining the current WK as B_eCharacteristic weight w of_e。

Take the value of a as 8, take B as an example_eAs the a-th bit information in the TK, obtaining the bitmap in the e-th period detection window_e00110000, initializing WK to 10000000, current bitmap_eIs 0, will bitmap_eRight shift by one bit 00011000, right shift by one bit WK 01000000, and loop execution until bitmap_eIs 1, the value of WK is B_eCharacteristic weight w of_e. Obtaining the feature weight w by adopting the operation as step S542 to step S572_eIncrease the acquisition characteristic weight w_eThe efficiency of (c).

The fifth embodiment is particularly suitable for application scenarios with low Summary update frequency, that is, application scenarios with Summary update frequency lower than a preset update frequency threshold. The method and the device particularly adopt bitmap to store the periodic change rate of Summary, and greatly reduce the space occupied by data storage. Obtaining feature weights w based on bitmaps_eThe method has the advantages of high operation speed and high accuracy, and improves the characteristic weight w_eAccuracy and efficiency of the process. Therefore, the accuracy and the training efficiency of training the industrial control network vulnerability prediction model are improved, and the accuracy and the prediction efficiency of predicting the industrial control network vulnerability outbreak probability are further improved. Reasonable defense measures are set based on the method, and the safety and the stability of the industrial control network are improved.

The third embodiment to the fifth embodiment describe three sets of methods for determining the corresponding Summary feature weight of each Summary text, and the sixth embodiment further describes a method for determining the original feature parameter value g (Str)_e) Based on g (Str)_e) And determining the corresponding Summary feature parameter value PCS of each Summary text according to the corresponding feature weight_e。g(Str_e) Specifically, g (Str) can be obtained based on the Summary text feature based on the existing feature processing algorithm_e). G (Str) can also be obtained based on the sub-scheme described in example six_e)

Example six,

The system comprises a preset industrial internet stop word bank, wherein stop words commonly used in the field of industrial internet are stored in the internet stop word bank. The text sequence of Summary corresponding to each sample vulnerability id is { Str₁,Str₂,…}，Str_eThe value range of e is 1 to infinity for the Summary text corresponding to the e-th updating period.

The computer program stored in the storage medium includes a sixth computer program that, when executed by the processor, implements the steps of:

step S601, stopping Str based on the industrial Internet_eThe industrial internet stop words in (1) are removed, and the Str is paired at the position of the industrial internet stop words_eThe segmentation is carried out to generate a corresponding text segment sequence { Fr_e1, Fr_e2,…Fr_eI}, Fr_eiIs Str_eI ranges from 1 to I, and I is Str_eTotal number of text segments.

Wherein, taking ABCDEFG as an example of a piece of text, each letter represents a word, and assuming that C and E are stop words in the industrial Internet stop word bank, C and E are removed, and the rest text is divided into three text segments AB, D and FG.

Step S602, for each Str_eEach Fr of_eiExecuting preset N-gram word segmentation processing, wherein N is a positive integer and the value range is [ Kn₁, Kn₂]Each Str_eAll Fr of_eiThe word segmentation is merged and de-duplicated to obtain a corresponding word segmentation vector FB_e。

It should be noted that if the N-gram word segmentation is directly performed on each Summary, because the number of Summary texts is huge, if the word segmentation results of all the Summary texts N-gram are directly subjected to one-hot coding, the vector dimension is too large, the required calculation amount is large, and the data processing efficiency is low. In this embodiment, each Summary is segmented based on stop words in step S601, and then the segmented text segments are N-gram word segmentation one by one, so that vector dimensionality can be greatly reduced, and data processing efficiency can be improved. The specific word segmentation process of the N-gram is prior art and will not be described herein. Preferably, kn₁A value of 3, kn₂The value is 6.

Step S603, all FBs_eAnd combining and de-duplicating the participles in the database to obtain a participle set FC, and determining the number of the participles of the FC as the dimension of one-hot coding.

Step S604, carrying out FB on participle vectors based on one-hot coded dimension pair_eOne-hot coding to obtain each Str_eThe original characteristic parameter value of (2).

The specific encoding process of one-hot encoding is prior art and will not be described herein. It will be appreciated that when the word vector FB is bisected_eAfter one-hot coding, the corresponding Str can be obtained based on the coding result_eThe original characteristic parameter value of (2).

Step S605, Str corresponding to vulnerability id based on sample_eAnd establishing a model input vector by using the original characteristic parameter values, training to obtain an industrial control network vulnerability prediction model, and predicting the industrial control network vulnerability outbreak probability based on the industrial control network vulnerability prediction model.

The step S605 can be directly based on Str_eThe original characteristic parameter value is combined with other vulnerability characteristic parametersModel input vectors are built, and in order to further improve accuracy of Summary characteristic parameter values, each Str can be subjected to_eGiving corresponding weight, as an example, in the step S605, based on the Str corresponding to the sample vulnerability id_eThe original characteristic parameter value modeling input vector comprises:

step S615, Str corresponding to vulnerability id based on sample_eOriginal characteristic parameter value g (Str) of_e) And corresponding feature weights w_eDetermining each Str_eCorresponding Summary characteristic parameter value PCS_e=w_e*g(Str_e) And constructing a model input vector based on the Summary characteristic parameter values corresponding to the sample vulnerability id.

Wherein, Str_eCorresponding feature weight w_eBased on Str_eAnd the current Summary text is determined based on changes in the historical Summary text. Specifically, at least one of the third, fourth and fifth embodiments may be adopted to determine w_eAnd will not be described herein.

In order to further improve the processing efficiency and accuracy of the Summary parameter value, the industrial internet decommissioned thesaurus may be updated, and for example, when the processor executes the sixth computer program, the processor further implements an industrial internet decommissioned thesaurus updating process, including the following steps:

step S600, initializing N = Kn2 in the N-gram,

s610, dividing the Summary texts corresponding to all vulnerability ids into text segments based on the industrial internet stop word library, removing industrial internet stop words, and performing N-gram word segmentation processing on each text segment to obtain an N-gram word segmentation quantity list;

step S620, adding the N-gram participles with the N-gram participle quantity larger than a preset participle quantity threshold value D3 into the industrial Internet disabled word stock, and judging whether Kn is larger than Kn or not₁If yes, setting Kn = Kn-1, returning to step S610, if Kn is equal to Kn₁And ending the process of updating the lexicon by using the industrial internet.

Through the steps S600-S620, the industrial internet disabled word stock is updated by combining N-gram processing on all the Summary texts, so that the disabled word stock is synchronously updated based on the updating conditions of the Summary texts, and the processing efficiency and accuracy of obtaining Summary parameter values are improved.

Preferably, D3= f [ [ solution ] ]

，SN，avg(Kn)]Wherein D3 is substituted with

Is positively correlated with SN, is negatively correlated with avg (Kn) D3, and is the total number of total Summary of all holes, L_jAvg (N) is the average of all values of N in the N-gram.

The sixth embodiment reduces the number of word segments after N-gram processing on all Summary texts by processing the stop words and segments of the Summary texts through the industrial internet stop word bank, thereby reducing the word segment vector FB_eThe coding dimension of one-hot coding is improved, and Str acquisition is improved_eThe efficiency and the accuracy of the original characteristic parameter values are improved, so that the accuracy and the training efficiency of training the industrial control network vulnerability prediction model are improved, the accuracy and the prediction efficiency of predicting the vulnerability outbreak probability of the industrial control network are improved, reasonable defense measures are set based on the method, and the safety and the stability of the industrial control network are improved.

Example seven,

A server comprising the system of at least one of embodiments one through six.

The server can quickly and accurately train the industrial control network vulnerability prediction model based on the internet vulnerability characteristic parameters and the industrial control network vulnerability characteristic parameters, so that the industrial control network vulnerability outbreak probability can be quickly and accurately predicted based on the industrial control network vulnerability prediction model, reasonable defense measures are set based on the method, and the safety and the stability of the industrial control network are improved.

It should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the steps as a sequential process, some of the steps may be performed in parallel, concurrently or at the same time. In addition, the order of the steps may be rearranged. A process may be terminated when its operations are completed, but may have additional steps not included in the figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

It is to be understood that the invention is not limited to the specific embodiments disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention as defined by the appended claims.

Claims (7)

1. A system for predicting industrial control network bugs based on Summary word segmentation features is characterized in that,

the system comprises a processor, a database and a storage medium which stores a computer program, wherein the processor is in communication connection with the database, an internet vulnerability characteristic parameter list and an industrial control network vulnerability characteristic parameter list which correspond to all internet vulnerability ids are stored in the database, the internet vulnerability characteristic parameters which correspond to the internet vulnerability ids comprise Summary, and the Summary represents a vulnerability description text; the computer program stored in the storage medium includes a fourth computer program that, when executed by the processor, performs the steps of:

step S400, obtaining a text sequence { Str) of each sample vulnerability id in corresponding Summary from the database₁,Str₂,…}，Str_eThe value range of e is 1 to infinity for the Summary text corresponding to the e-th updating period;

step S401, for Str_ePerforming word segmentation processing, and stopping words by using a preset stopping word bank to obtain Str_eCorresponding participle set A_e；

Step S402, when e is equal to 1, according to A_eDetermining the number of participles Str_eCharacteristic weight w of_e；

Step S403, when e>At 1 time, Str is compared_e-1And Str_eIf the text information of (1) is completely consistent with the text information of (1), setting w_e＝w_e-1If Str_e-1And Str_eIf the text information is not completely consistent, the word segmentation set A is divided_eAnd a participle set A_e-1Performing set difference set operation to obtain A_eRelative to A_e-1Difference set fractional word number A_e-A_e-1And A is_e-1Relative to A_eDifference set part word number A of_e-1- A_eSet up w_e＝[(A_e-A_e-1)/(A_e-1- A_e)]*w_e-1；

Step S404, based on each Str_eCharacteristic weight w of_eAnd Str_eDetermining each Str_eCorresponding Summary characteristic parameter value PCS_e＝w_e*g(Str_e) Wherein, g (Str)_e) Is based on Str_eDetermining the original characteristic parameter value;

s405, constructing a model input vector based on the Summary characteristic parameter values corresponding to the sample vulnerability ids, training to obtain an industrial control network vulnerability prediction model, and predicting the industrial control network vulnerability outbreak probability based on the industrial control network vulnerability prediction model.

2. The system of claim 1,

the step S402 includes:

step S412, A_eNumber of participles SA_eWith a predetermined first threshold value of the number of sub-words SU_minAnd a second participle number threshold SU_maxComparison, wherein SU_min<SU_maxIf SA_e<SU_minThen set w_e＝ws_min，ws_minIs a preset third feature weight threshold if SA_e>SU_maxThen set w_e＝ws_max，ws_maxIs a preset fourth characteristic weight threshold value, if the preset third characteristic weight threshold value is [ SU ]_min，SU_max]Then set w_e＝k₂*SA_eWherein k is₂Is a preset second linear change coefficient.

3. The system of claim 2,

k₂is set to (ws)_max-ws_min)/ws_max。

4. The system of claim 1,

the step S401 further includes:

step 422, if { Str₁,Str₂… } consecutive first ns strs_eA of (A)_eIs empty, A_e+1If not, Str is set_ns+1Characteristic weight w of_ns+1＝ws_max，ws_maxIs a preset third feature weight threshold, then, e-ns +2 is initialized, and step S403 is performed.

5. The system of claim 2,

ws_minset to 0, ws_maxIs set to 1.

6. The system of claim 1,

in step S405, a model input vector is constructed based on the Summary characteristic parameter values corresponding to the sample vulnerability ids, and an industrial control network vulnerability prediction model is obtained through training, including:

step S415, determining a model input vector of each sample vulnerability id according to the Summary characteristic parameter value corresponding to the sample vulnerability id, a preset internet vulnerability characteristic parameter and a preset industrial control network vulnerability characteristic parameter;

and S425, training based on model input vectors corresponding to sample vulnerability ids and the true value of the vulnerability outbreak probability of the industrial control network to obtain the industrial control network vulnerability prediction model.

7. A server, characterized in that it comprises a system according to any one of claims 1 to 6.

Images