CN108683666A - A kind of web page identification method and device - Google Patents
A kind of web page identification method and device Download PDFInfo
- Publication number
- CN108683666A CN108683666A CN201810468614.0A CN201810468614A CN108683666A CN 108683666 A CN108683666 A CN 108683666A CN 201810468614 A CN201810468614 A CN 201810468614A CN 108683666 A CN108683666 A CN 108683666A
- Authority
- CN
- China
- Prior art keywords
- page
- target webpage
- feature
- preset
- page data
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1416—Event detection, e.g. attack signature detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/02—Network architectures or network communication protocols for network security for separating internal from external traffic, e.g. firewalls
- H04L63/0227—Filtering policies
- H04L63/0236—Filtering by address, protocol, port number or service, e.g. IP-address or URL
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
Abstract
An embodiment of the present invention provides a kind of web page identification method and devices, are related to technical field of network security, and the method is applied to safety equipment, the method includes：The web-page requests that user terminal is sent are received, the URL of target webpage to be visited is carried in the web-page requests；According to the URL of the target webpage, the page data of the target webpage is obtained from the server of the target webpage；According to preset feature extraction rule and the page data, the page feature of the target webpage is determined；According to the page feature and preset page classifications model, judges whether the target webpage is illegal web page, if the target webpage is illegal web page, send a warning message to the user terminal.The discrimination of illegal website can be improved using the present invention.
Description
Technical field
The present invention relates to technical field of network security, more particularly to a kind of web page identification method and device.
Background technology
With the explosive increase of internet data, the fishing of the private informations such as account No., the password of user's submission is stolen
Fishnet station is also more and more.The page of fishing website and actual site interface are completely the same, to inveigle user to input the quick of individual
Feel information.For example, fishing website submits the privacy informations such as account and password, user cheating to fill out to get the winning number in a bond for bait requirement visitor
Write the information such as identity information, bank account.For another example, fishing website imitates the on-line payments webpages such as Taobao, industrial and commercial bank, gains user's silver by cheating
Row card information or Alipay account.Frequently occurring for fishing website brings great danger to the privacy and property safety of isdn user
Evil.
In order to avoid fishing website steals user information, technical staff can establish black list database in safety equipment,
Be stored in the black list database technical staff collect in advance fishing website URL (Uniform Resoure Locator,
Uniform resource locator).Safety equipment, can be first by the URL of the website and black name when detecting user terminal access website
URL in single database is compared, if there are the URL in black list database, judges that the website is fishing website, to
User terminal returns to warning information, to prompt the user website as fishing website.If there is no should in black list database
URL, then it is fishing website to judge the website not, and safety equipment obtains the page data of the website according to the URL, and whole to user
End returns to the page data, so that user accesses the website.
However, the black list database is manually established, the URL of storage is not comprehensive enough, and lag is also compared in update,
Cause to identify that the discrimination of fishing website is relatively low.
Invention content
The embodiment of the present invention is designed to provide a kind of web page identification method and device, to improve the identification of illegal website
Rate.Specific technical solution is as follows：
In a first aspect, providing a kind of web page identification method, the method is applied to safety equipment, the method includes：
The web-page requests that user terminal is sent are received, the unification of target webpage to be visited is carried in the web-page requests
Resource localizer URL；
According to the URL of the target webpage, the page of the target webpage is obtained from the server of the target webpage
Data；
According to preset feature extraction rule and the page data, the page feature of the target webpage is determined；
According to the page feature and preset page classifications model, judge whether the target webpage is illegal web page,
If the target webpage is illegal web page, send a warning message to the user terminal.
Second aspect provides a kind of webpage identification device, and described device is applied to safety equipment, and described device includes：
Receiving module, the web-page requests for receiving user terminal transmission carry in the web-page requests to be visited
The uniform resource locator URL of target webpage；
First acquisition module obtains institute for the URL according to the target webpage from the server of the target webpage
State the page data of target webpage；
First determining module, for according to preset feature extraction rule and the page data, determining the target network
The page feature of page；
First sending module, for according to the page feature and preset page classifications model, judging the target network
Whether page is illegal web page, if the target webpage is illegal web page, is sent a warning message to the user terminal.
The third aspect provides a kind of safety equipment, including processor and machine readable storage medium, described machine readable
Storage medium is stored with the machine-executable instruction that can be executed by the processor, and the processor can perform by the machine
Instruction promotes：Realize any method and steps of claim 1-7.
Fourth aspect provides a kind of machine readable storage medium, is stored with machine-executable instruction, by processor tune
When with executing, the machine-executable instruction promotes the processor：Realize any method steps of claim 1-6
Suddenly.
PP174545
In the embodiment of the present invention, after safety equipment receives the web-page requests of user terminal transmission, according to the web-page requests
The URL of middle carrying obtains the page data of target webpage, then according to preset feature extraction from the server of target webpage
Rule and page data, determine the page feature of target webpage, according to page feature and preset page classifications model, judge mesh
It marks whether webpage is illegal web page, if target webpage is illegal web page, sends a warning message to user terminal.Based on above-mentioned
Processing, can judge whether target webpage is the illegal page, is not necessarily to according to the page feature and page classifications model of target webpage
Black list database manually is established, can be avoided because the data in black list database are not comprehensive, and leads to not identify non-
The case where net of justice station, improves the discrimination of illegal website.Certainly, it implements any of the products of the present invention or method must be needed not necessarily
To reach all the above advantage simultaneously.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is system framework figure provided in an embodiment of the present invention；
Fig. 2 is a kind of method flow diagram of web page identification method provided in an embodiment of the present invention；
Fig. 3 is a kind of example of web page identification method provided in an embodiment of the present invention；
Fig. 4 is a kind of structural schematic diagram of webpage identification device provided in an embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of webpage identification device provided in an embodiment of the present invention；
Fig. 6 is a kind of structural schematic diagram of webpage identification device provided in an embodiment of the present invention；
Fig. 7 is a kind of structural schematic diagram of webpage identification device provided in an embodiment of the present invention；
Fig. 8 is the structural schematic diagram of safety equipment provided in an embodiment of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
An embodiment of the present invention provides a kind of web page identification method, this method can be applied to safety equipment, which sets
It is standby to be connect respectively with the server in user terminal and network.As shown in Figure 1, being system frame provided in an embodiment of the present invention
Frame figure, including safety equipment, multiple user terminals and multiple servers.
As shown in Fig. 2, the processing procedure of this method may comprise steps of：
Step 201, the web-page requests that user terminal is sent are received.
Wherein, carried in the web-page requests target webpage to be visited URL (Uniform Resoure Locator,
Uniform resource locator).
In force, the application program for browsing webpage, such as the application of certain browser can be installed in user terminal
Program.When user desires access to some webpage (can be described as target webpage), user can open this in user terminal and apply journey
Then sequence clicks the corresponding icon of target webpage, or the network address of input target webpage, user terminal can then receive corresponding mesh
The access instruction for marking webpage, then can obtain the URL of preset target webpage, and then can generate the net for carrying the URL
Page request.User terminal can send the web-page requests to safety equipment, after safety equipment receives web-page requests, be asked to webpage
It asks and is parsed, obtain URL therein.In the embodiment of the present invention, target webpage can be the Html pages.
Step 202, according to the URL of target webpage, the page data of target webpage is obtained from the server of target webpage.
In force, after safety equipment gets the URL of target webpage, the page of target webpage can be obtained according to the URL
Face data.Specifically, safety equipment can regenerate web-page requests, the net according to the URL and preset message generating algorithm
The source address of page request is the address of safety equipment, in this way, safety equipment can be corresponding to target webpage with pseudo subscriber terminal
Server sends the web-page requests.Alternatively, the web-page requests can also be transmitted to target webpage by safety equipment according to the URL
Corresponding server.
After server receives the web-page requests, the web-page requests can be responded, to return to the page data of target webpage.
After safety equipment receives page data, will not the page data be directly transmitted to user terminal, but execute step 203,
To judge whether target webpage is the illegal page.
Step 203, according to preset feature extraction rule and page data, the page feature of target webpage is determined.
In force, feature extraction rule can be previously stored in safety equipment, this feature extracting rule can be by skill
Art personnel set.After safety equipment receives page data, according to preset feature extraction rule and the page data, really
Set the goal the page feature of webpage.
Optionally, determining the concrete processing procedure of page feature can be：From the page data of target webpage, extraction the
One target component determines the page feature of target webpage according to the first object parameter extracted.
Wherein, first object parameter can rule of thumb be set by technical staff, and in the embodiment of the present invention, target component is extremely
Include less the page URL of target pages, the preset field in list, heading message, web page element information and target webpage page
The preset number URL for including in face data.Wherein, the page URL of target pages is the URL of target webpage, can be denoted as Page_
URL；Heading message is in page data<title>, Page_Title can be denoted as；Web page element information is in page data
<meta name>, Page_Meta can be denoted as；The preset number URL for including in the page data of target webpage is target webpage
Page data in include URL, Content_URL can be denoted as respectivelyi(i (1, n)), n is preset number, and by [Content_
URL1,Content_URL2... ..., Content_URLi] it is denoted as Content_URL；Preset field in list can be target
The content of the action fields in form (i.e. list) in webpage, can be denoted as Page_Action.In addition, target component may be used also
To include<head>The JS scripts loaded in domain, can be denoted as Head_Js, and randomly selected from page data a section
It falls, Body_Segment can be denoted as.First object parameter can also include the other parameters in page data, the embodiment of the present invention
It does not limit.
In force, multiple parameters have been generally comprised in page data, technical staff can in advance match in safety equipment
It sets and needs the parameter (i.e. first object parameter) extracted can be according to preset field after safety equipment receives page data
Extraction algorithm searches first object parameter in page data, and then extracts first object parameter, then according to the extracted
One target component determines the page feature of first object webpage.In one implementation, safety equipment can will extract
First object parameter, the page feature as target webpage.In practice, the number for the URL that the page data of target webpage includes
Mesh may be more than preset number, at this point, safety equipment can be pre- before extracting according to the URL sequences of the appearance in page data
If number URL.
For example, safety equipment after extracting target component in target webpage, can obtain a feature vector a, then
Using this feature vector as the page feature of target webpage, wherein：
A=[Page_URL, Page_Action, Page_Title, Page_Meta, Content_URL, Head_Js,
Body_Segment]。
Optionally, safety equipment can be combined with the page data for the URL that target webpage is included, and determine target webpage
Page feature, specific processing procedure can be as follows：Obtain the page data of the corresponding linked web pages of preset number URL；Needle
To each linked web pages, the second target component is extracted from the page data of the linked web pages, by first object parameter and from
The second target component extracted in preset number linked web pages, the page feature as target webpage.
Wherein, the second target component include at least the page URL of linked web pages, the preset field in list, heading message,
The preset number URL for including in the page data of web page element information and linked web pages.Wherein, the page URL of linked web pages
For the URL of linked web pages, A-Page_URL can be denoted as；Heading message is in page data<title>, A-Page_ can be denoted as
Title；Web page element information is in page data<meta name>, A-Page_Meta can be denoted as；The page of linked web pages
The preset number URL for including in data is the URL for including in the page data of linked web pages, can be denoted as A-Content_ respectively
URLi(i ∈ (1, n)), n is preset number, and by [A-Content_URL1,A-Content_URL2... ..., A-Content_
URLi] it is denoted as A-Content_URL；；Preset field in list can be in the form (i.e. list) in linked web pages
The content of action fields can be denoted as A-Page_Action.In addition, the second target component can also include<head>Add in domain
The JS scripts of load can be denoted as A-Head_Js, and the paragraph randomly selected from the page data of linked web pages, can remember
For A-Body_Segment.Second target component can also include the other parameters in page data, and the embodiment of the present invention is not done
It limits.
In force, multiple linked web pages access entrances have been generally comprised in target webpage, user can be in target webpage
The corresponding icon of middle click linked web pages, accesses the linked web pages.Correspondingly, can include chain in the web data of target webpage
Meet the URL of webpage.
After safety equipment extracts the preset number URL for including in the page data of target webpage, for each URL,
Safety equipment can generate the web-page requests for including the URL, then by the net according to the URL and preset message generating algorithm
Page request is sent to server.After server receives the web-page requests, the web-page requests can be responded, to return to this URL pairs
The page data for the linked web pages answered.
It, can be from the link net after safety equipment receives the page data of the linked web pages for each linked web pages
In the page data of page, the second target component, the second target component (i.e. feature vector) that will be extracted, as the link are extracted
The page feature of webpage, specific processing procedure is with reference to above description, and details are not described herein again.In this way, safety equipment can obtain
The feature vector for the preset number linked web pages that the feature vector and target webpage of target webpage include, to obtain spy
Matrix is levied, for example, preset number is 5, then safety equipment can obtain eigenmatrix A=[a1,a2,a3,a4,a5,a6,], wherein
a1For the feature vector of target webpage, a2~a6For the feature vector of 5 linked web pages.Safety equipment can be by this feature matrix
Page feature as target webpage.
Optionally, safety equipment can first judge whether the web data of target webpage is normal page data, then again
Determine that page feature, specific processing procedure are：Judge whether the validation value that page data includes is preset normal page number
According to corresponding validation value；If validation value is the corresponding validation value of preset normal page data, execute according to preset spy
Extracting rule and page data are levied, determines the page feature step of target webpage；If validation value is not preset normal page
The corresponding validation value of data then sends error notification message to user terminal.
In force, due to server failure etc., the page data that server returns may have exception, because
This, would generally be pre-set in page data there are one verifying field, the verifying field be used for storing page data verification
Value, safety equipment can identify whether the page data received is normal page data according to the validation value.
After safety equipment receives page data, the verifying field can be parsed in the page data, tested to obtain
Card value illustrates that the page data is normal page if the validation value is the corresponding validation value of preset normal page data
Data, safety equipment can then cache the page data, and execute according to preset feature extraction rule and page number
According to determining the page feature step of target webpage.If validation value is not the corresponding validation value of preset normal page data,
Illustrate that the page data is abnormal data (for example the page data is mess code data or invalid data), safety equipment is to user
Terminal sends error notification message, and without other processing.After user terminal receives error notification message, display is corresponding
Miscue information, such as " page can not access " or " page that you access is not present " etc..For example, if validation value is
200, then page data is judged for normal page data, if validation value is 404, judges page data for abnormal data.
In this way, safety equipment can judge page data for normal page data when, just execution step 203, if page
Face data is abnormal data, will be without processing, so as to save the process resource of safety equipment.
Step 204, according to page feature and preset page classifications model, judge whether target webpage is illegal web page,
If target webpage is illegal web page, send a warning message to user terminal.
In force, the page feature of target webpage can be input to page classifications mould trained in advance by safety equipment
In type, page classifications model can then export the corresponding classification results of the target webpage, and classification results are used to indicate the target webpage
Whether it is illegal web page.If classification results indicate that the target webpage is illegal web page, safety equipment can be sent out to user terminal
Warning information is sent, to prompt ownership goal webpage as illegal web page, to prevent user's access target webpage, improves user's letter
The safety of breath.
If classification results indicate that the target webpage is legal webpage, safety equipment can be by the page data of target webpage
It is sent to user terminal, so that user terminal is according to page data display target webpage.
It should be noted that after receiving page data, it is aobvious can first to extract basis from page data for safety equipment
Basic display data is sent to user terminal by registration evidence, wherein basic display data is that the basic framework of webpage is corresponding aobvious
Registration evidence.In this way, user terminal can be based on display data, the basic framework of first display target webpage, so that at target webpage
State in load, so as to improve user experience.After safety equipment judgement target webpage is legal webpage, then by mesh
The mark specific content-data of webpage issues user terminal, so that user terminal shows complete target webpage.
Optionally, the present embodiment additionally provides the training method of page classifications model, and concrete processing procedure is as follows：Safety is set
Standby to obtain pre-stored multiple training samples, training sample includes the page feature of illegal web page and the page spy of legal webpage
Sign；Based on multiple training samples, preset initial neural network model is trained, page classifications model is obtained.
In force, initial neural network model can be built in safety equipment, which can be
Using BP (back propagation, backpropagation) neural networks or convolutional neural networks.Technical staff can be initial to this
Neural network model is initialized, for example, setting input layer to hidden layer weights ωmn, hidden layer to output layer weights vlkWith
And error threshold Δt.Multiple training samples can also be stored in safety equipment, training sample includes the page feature of illegal web page
With the page feature of legal webpage.Specifically, technical staff can collect page data, the Yi Jixiang of multiple illegal web pages in advance
With the page data of the legal webpage of quantity, and the page feature of each webpage is determined by safety equipment respectively, extract the page
The process of feature is referred to above description, and details are not described herein again.
Safety equipment can be based on multiple training samples, be trained to preset initial neural network model, obtain page
Face disaggregated model, specific processing procedure are：Training sample is input to initial neural network model, output training sample corresponds to
Testing feature vector；By back-propagation algorithm, using the corresponding testing feature vector of training sample, to initial neural network
The model parameter that model includes is adjusted, and obtains page classifications model, and model parameter includes at least input layer to the power of hidden layer
The weights of value and hidden layer to output layer.
In force, multiple training samples can be sequentially inputted in initial neural network model by safety equipment, for
Each training sample, initial neural network model then it is corresponding to calculate the training sample according to preset neural network algorithm
Testing feature vector, and the error of the testing feature vector and preset desired character vector is calculated, and then judge that the error is
It is no to be less than preset error threshold.If the error is greater than or equal to preset error threshold, according to preset backpropagation
Algorithm, the weights ω of adjustment input layer to hidden layermnWith the weights v of hidden layer to output layerlk, then, safety equipment input is next
Training sample, and above-mentioned processing is repeated, until the error determined is less than preset error threshold.When what is determined
When error is less than preset error threshold, the weights ω of input layer that safety equipment can be current to neural network to hidden layermn, hidden layer
To the weights v of output layerlkAnd error threshold ΔtIt is stored, to determine page classifications model.
As shown in figure 3, being a kind of example of web page identification method provided in an embodiment of the present invention, concrete processing procedure is：
Step 301, the web-page requests that user terminal is sent are received.
Step 302, according to the URL of target webpage, the page data of target webpage is obtained from the server of target webpage.
Step 303, judge whether the validation value that page data includes is the corresponding validation value of preset normal page data.
If not, thening follow the steps 304；Otherwise, step 305~step 306 is executed.
Step 304, error notification message is sent to user terminal.
Step 305, according to preset feature extraction rule and page data, the page feature of target webpage is determined.
Step 306, according to page feature and preset page classifications model, judge whether target webpage is legal webpage.
If not, thening follow the steps 307；Otherwise, step 308 is executed.
Step 307, it sends a warning message to user terminal.
Step 308, the page data of target webpage is sent to user terminal, so that user terminal is aobvious according to page data
Show target webpage.
In the embodiment of the present invention, after safety equipment receives the web-page requests of user terminal transmission, according to the web-page requests
The URL of middle carrying obtains the page data of target webpage, then according to preset feature extraction from the server of target webpage
Rule and page data, determine the page feature of target webpage, according to page feature and preset page classifications model, judge mesh
It marks whether webpage is illegal web page, if target webpage is illegal web page, sends a warning message to user terminal.Based on above-mentioned
Processing, can judge whether target webpage is the illegal page, is not necessarily to according to the page feature and page classifications model of target webpage
Black list database manually is established, can be avoided because the data in black list database are not comprehensive, and leads to not identify non-
The case where net of justice station, improves the discrimination of illegal website.
It based on the same technical idea, should as shown in figure 4, the embodiment of the present invention additionally provides a kind of webpage identification device
Device is applied to safety equipment, which includes：
Receiving module 410, the web-page requests for receiving user terminal transmission carry mesh to be visited in web-page requests
Mark the URL of webpage；
First acquisition module 420 obtains target network for the URL according to target webpage from the server of target webpage
The page data of page；
First determining module 430, for according to preset feature extraction rule and page data, determining the page of target webpage
Region feature；
First sending module 440, for according to page feature and preset page classifications model, whether judging target webpage
It is sent a warning message to user terminal for illegal web page if target webpage is illegal web page.
Optionally, as shown in figure 5, the device further includes：
Second sending module 450 sends out the page data of target webpage if not being illegal web page for target webpage
User terminal is given, so that user terminal is according to page data display target webpage.
Optionally, the first determining module 430, is specifically used for：
From the page data of the target webpage, first object parameter is extracted, the first object parameter includes：It is described
The page URL of target pages, the page of the preset field in list, heading message, web page element information and the target webpage
The preset number URL for including in data；
According to the first object parameter extracted, the page feature of the target webpage is determined.
Optionally, the first determining module 430, is specifically used for：
Obtain the page data of the corresponding linked web pages of the preset number URL；
For each linked web pages, the second target component, second mesh are extracted from the page data of the linked web pages
Marking parameter includes:The page URL of the linked web pages, the preset field in list, heading message, web page element information and described
The preset number URL for including in the page data of linked web pages；
By the first object parameter and the second target component extracted from the preset number linked web pages,
Page feature as the target webpage.
Optionally, include validation value in page data, as shown in fig. 6, the device further includes：
Judgment module 460, for judging whether the validation value that page data includes is that preset normal page data correspond to
Validation value；
Second determining module 470 triggers if being the corresponding validation value of preset normal page data for validation value
First determining module 430 executes the page feature step that target webpage is determined according to preset feature extraction rule and page data
Suddenly；
Third sending module 480, if not being the corresponding validation value of preset normal page data for validation value, to
User terminal sends miscue information.
Optionally, as shown in fig. 7, the device further includes：
Second acquisition module 490, for obtaining pre-stored multiple training samples, training sample includes illegal web page
The page feature of page feature and legal webpage；
Training module 4100 is trained preset initial neural network model, obtains for being based on multiple training samples
To page classifications model.
Optionally, the training module 4100, is specifically used for：
The training sample is input to the initial neural network model, it is special to export the corresponding test of the training sample
Sign vector；
By back-propagation algorithm, using the corresponding testing feature vector of the training sample, to the initial nerve net
The model parameter that network model includes is adjusted, and obtains the page classifications model, and the model parameter includes at least input layer
To hidden layer weights and hidden layer to output layer weights.
In the embodiment of the present invention, after safety equipment receives the web-page requests of user terminal transmission, according to the web-page requests
The URL of middle carrying obtains the page data of target webpage, then according to preset feature extraction from the server of target webpage
Rule and page data, determine the page feature of target webpage, according to page feature and preset page classifications model, judge mesh
It marks whether webpage is illegal web page, if target webpage is illegal web page, sends a warning message to user terminal.Based on above-mentioned
Processing, can judge whether target webpage is the illegal page, is not necessarily to according to the page feature and page classifications model of target webpage
Black list database manually is established, can be avoided because the data in black list database are not comprehensive, and leads to not identify non-
The case where net of justice station, improves the discrimination of illegal website.
The embodiment of the present application also provides a kind of safety equipments, as shown in figure 8, including processor 801, communication interface 802,
Memory 803 and communication bus 804, wherein processor 801, communication interface 802, memory 803 are complete by communication bus 804
At mutual communication,
Memory 803, for storing computer program；
Processor 801, when for executing the program stored on memory 803, so that the safety equipment executes following step
Suddenly, which includes：
The web-page requests that user terminal is sent are received, the unification of target webpage to be visited is carried in the web-page requests
Resource localizer URL；
According to the URL of the target webpage, the page of the target webpage is obtained from the server of the target webpage
Data；
According to preset feature extraction rule and the page data, the page feature of the target webpage is determined；
According to the page feature and preset page classifications model, judge whether the target webpage is illegal web page,
If the target webpage is illegal web page, send a warning message to the user terminal.
Optionally, the method further includes：
If the target webpage is not illegal web page, the page data of the target webpage is sent to the user
Terminal, so that the user terminal shows the target webpage according to the page data.
Optionally, described according to preset feature extraction rule and the page data, determine the page of the target webpage
Region feature, including：
From the page data of the target webpage, first object parameter is extracted, the first object parameter includes：It is described
The page URL of target pages, the page of the preset field in list, heading message, web page element information and the target webpage
The preset number URL for including in data；
According to the first object parameter extracted, the page feature of the target webpage is determined.
Optionally, the first object parameter that the basis extracts, determines the page feature of the target webpage, packet
It includes：
Obtain the page data of the corresponding linked web pages of the preset number URL；
For each linked web pages, the second target component, second mesh are extracted from the page data of the linked web pages
Marking parameter includes:The page URL of the linked web pages, the preset field in list, heading message, web page element information and described
The preset number URL for including in the page data of linked web pages；
By the first object parameter and the second target component extracted from the preset number linked web pages,
Page feature as the target webpage.
Optionally, include validation value in the page data, it is described according to preset feature extraction rule and the page
Data, before the page feature for determining the target webpage, the method further includes：
Judge whether the validation value that the page data includes is the corresponding validation value of preset normal page data；
If the validation value is the corresponding validation value of preset normal page data, execute described according to preset spy
Extracting rule and the page data are levied, determines the page feature step of the target webpage；
If the validation value is not the corresponding validation value of the preset normal page data, to the user terminal
Send miscue information.
Optionally, the method further includes：
Pre-stored multiple training samples are obtained, the training sample includes the page feature of illegal web page and legal net
The page feature of page；
Based on the multiple training sample, preset initial neural network model is trained, obtains the page point
Class model.
Optionally, described to be based on the multiple training sample, preset initial neural network model is trained, is obtained
The page classifications model, including：
The training sample is input to the initial neural network model, it is special to export the corresponding test of the training sample
Sign vector；
By back-propagation algorithm, using the corresponding testing feature vector of the training sample, to the initial nerve net
The model parameter that network model includes is adjusted, and obtains the page classifications model, and the model parameter includes at least input layer
To hidden layer weights and hidden layer to output layer weights.
Machine readable storage medium may include RAM (Random Access Memory, random access memory), also may be used
To include NVM (Non-Volatile Memory, nonvolatile memory), for example, at least a magnetic disk storage.In addition, machine
Device readable storage medium storing program for executing can also be at least one storage device for being located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including CPU (Central Processing Unit, central processing
Device), NP (Network Processor, network processing unit) etc.；Can also be DSP (Digital Signal Processing,
Digital signal processor), ASIC (Application Specific Integrated Circuit, application-specific integrated circuit),
FPGA (Field-Programmable Gate Array, field programmable gate array) or other programmable logic device are divided
Vertical door or transistor logic, discrete hardware components.
In the embodiment of the present invention, after safety equipment receives the web-page requests of user terminal transmission, according to the web-page requests
The URL of middle carrying obtains the page data of target webpage, then according to preset feature extraction from the server of target webpage
Rule and page data, determine the page feature of target webpage, according to page feature and preset page classifications model, judge mesh
It marks whether webpage is illegal web page, if target webpage is illegal web page, sends a warning message to user terminal.Based on above-mentioned
Processing, can judge whether target webpage is the illegal page, is not necessarily to according to the page feature and page classifications model of target webpage
Black list database manually is established, can be avoided because the data in black list database are not comprehensive, and leads to not identify non-
The case where net of justice station, improves the discrimination of illegal website.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Each embodiment in this specification is all made of relevant mode and describes, identical similar portion between each embodiment
Point just to refer each other, and each embodiment focuses on the differences from other embodiments.Especially for device reality
For applying example, since it is substantially similar to the method embodiment, so description is fairly simple, related place is referring to embodiment of the method
Part explanation.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (16)
1. a kind of web page identification method, which is characterized in that the method is applied to safety equipment, the method includes：
The web-page requests that user terminal is sent are received, the unified resource of target webpage to be visited is carried in the web-page requests
Locator URL；
According to the URL of the target webpage, the page data of the target webpage is obtained from the server of the target webpage；
According to preset feature extraction rule and the page data, the page feature of the target webpage is determined；
According to the page feature and preset page classifications model, judge whether the target webpage is illegal web page, if
The target webpage is illegal web page, then sends a warning message to the user terminal.
2. according to the method described in claim 1, it is characterized in that, the method further includes：
If the target webpage is not illegal web page, it is whole that the page data of the target webpage is sent to the user
End, so that the user terminal shows the target webpage according to the page data.
3. according to the method described in claim 1, it is characterized in that, described according to preset feature extraction rule and the page
Data determine the page feature of the target webpage, including：
From the page data of the target webpage, first object parameter is extracted, the first object parameter includes：The target
The page URL of the page, the page data of the preset field in list, heading message, web page element information and the target webpage
In include preset number URL；
According to the first object parameter extracted, the page feature of the target webpage is determined.
4. according to the method described in claim 3, it is characterized in that, the first object parameter that the basis extracts, really
The page feature of the fixed target webpage, including：
Obtain the page data of the corresponding linked web pages of the preset number URL；
For each linked web pages, the second target component, the second target ginseng are extracted from the page data of the linked web pages
Number includes:Page URL, the preset field in list, heading message, web page element information and the link of the linked web pages
The preset number URL for including in the page data of webpage；
By the first object parameter and the second target component extracted from the preset number linked web pages, as
The page feature of the target webpage.
5. according to the method described in claim 1, it is characterized in that, including validation value in the page data, the basis is pre-
If feature extraction rule and the page data, before the page feature for determining the target webpage, the method further includes：
Judge whether the validation value that the page data includes is the corresponding validation value of preset normal page data；
If the validation value is the corresponding validation value of preset normal page data, executes and described carried according to preset feature
Rule and the page data are taken, determines the page feature step of the target webpage；
If the validation value is not the corresponding validation value of the preset normal page data, sent to the user terminal
Miscue information.
6. according to the method described in claim 1, it is characterized in that, the method further includes：
Pre-stored multiple training samples are obtained, the training sample includes the page feature of illegal web page and legal webpage
Page feature；
Based on the multiple training sample, preset initial neural network model is trained, obtains the page classifications mould
Type.
7. according to the method described in claim 6, it is characterized in that, described be based on the multiple training sample, to preset first
Beginning neural network model is trained, and obtains the page classifications model, including：
The training sample is input to the initial neural network model, export the corresponding test feature of the training sample to
Amount；
By back-propagation algorithm, using the corresponding testing feature vector of the training sample, to the initial neural network mould
The model parameter that type includes is adjusted, and obtains the page classifications model, and the model parameter includes at least input layer to hidden
Layer weights and hidden layer to output layer weights.
8. a kind of webpage identification device, which is characterized in that described device is applied to safety equipment, and described device includes：
Receiving module, the web-page requests for receiving user terminal transmission carry target to be visited in the web-page requests
The uniform resource locator URL of webpage；
First acquisition module obtains the mesh for the URL according to the target webpage from the server of the target webpage
Mark the page data of webpage；
First determining module, for according to preset feature extraction rule and the page data, determining the target webpage
Page feature；
First sending module, for according to the page feature and preset page classifications model, judging that the target webpage is
It is no to be sent a warning message to the user terminal for illegal web page if the target webpage is illegal web page.
9. device according to claim 8, which is characterized in that described device further includes：
Second sending module, if not being illegal web page for the target webpage, by the page data of the target webpage
It is sent to the user terminal, so that the user terminal shows the target webpage according to the page data.
10. device according to claim 8, which is characterized in that first determining module is specifically used for：
From the page data of the target webpage, first object parameter is extracted, the first object parameter includes：The target
The page URL of the page, the page data of the preset field in list, heading message, web page element information and the target webpage
In include preset number URL；
According to the first object parameter extracted, the page feature of the target webpage is determined.
11. device according to claim 10, which is characterized in that first determining module is specifically used for：
Obtain the page data of the corresponding linked web pages of the preset number URL；
For each linked web pages, the second target component, the second target ginseng are extracted from the page data of the linked web pages
Number includes:Page URL, the preset field in list, heading message, web page element information and the link of the linked web pages
The preset number URL for including in the page data of webpage；
By the first object parameter and the second target component extracted from the preset number linked web pages, as
The page feature of the target webpage.
12. device according to claim 8, which is characterized in that include validation value in the page data, described device is also
Including：
Judgment module is tested for judging whether validation value that the page data includes is that preset normal page data are corresponding
Card value；
Second determining module triggers institute if being the corresponding validation value of preset normal page data for the validation value
It is described according to preset feature extraction rule and the page data to state the execution of the first determining module, determines the target webpage
Page feature step；
Third sending module, if not being the corresponding validation value of the preset normal page data for the validation value,
Miscue information is sent to the user terminal.
13. device according to claim 8, which is characterized in that described device further includes：
Second acquisition module, for obtaining pre-stored multiple training samples, the training sample includes the page of illegal web page
The page feature of region feature and legal webpage；
Training module is trained preset initial neural network model, obtains institute for being based on the multiple training sample
State page classifications model.
14. device according to claim 13, which is characterized in that the training module is specifically used for：
The training sample is input to the initial neural network model, export the corresponding test feature of the training sample to
Amount；
By back-propagation algorithm, using the corresponding testing feature vector of the training sample, to the initial neural network mould
The model parameter that type includes is adjusted, and obtains the page classifications model, and the model parameter includes at least input layer to hidden
Layer weights and hidden layer to output layer weights.
15. a kind of safety equipment, which is characterized in that including processor and machine readable storage medium, the machine readable storage
Media storage has the machine-executable instruction that can be executed by the processor, and the processor is by the machine-executable instruction
Promote：Realize any method and steps of claim 1-6.
16. a kind of machine readable storage medium, which is characterized in that be stored with machine-executable instruction, by processor call and
When execution, the machine-executable instruction promotes the processor：Realize any method and steps of claim 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810468614.0A CN108683666B (en) | 2018-05-16 | 2018-05-16 | Webpage identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810468614.0A CN108683666B (en) | 2018-05-16 | 2018-05-16 | Webpage identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108683666A true CN108683666A (en) | 2018-10-19 |
| CN108683666B CN108683666B (en) | 2021-04-16 |
Family
ID=63806629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810468614.0A Active CN108683666B (en) | 2018-05-16 | 2018-05-16 | Webpage identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108683666B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059272A (en) * | 2018-11-02 | 2019-07-26 | 阿里巴巴集团控股有限公司 | A kind of page feature recognition methods and device |
| CN110401660A (en) * | 2019-07-26 | 2019-11-01 | 秒针信息技术有限公司 | Recognition methods, device, processing equipment and the storage medium of false flow |
| CN110674442A (en) * | 2019-09-17 | 2020-01-10 | 中国银联股份有限公司 | Page monitoring method, device, equipment and computer readable storage medium |
| CN110704867A (en) * | 2019-09-06 | 2020-01-17 | 翼集分电子商务(上海)有限公司 | Method, system, medium and apparatus for integral theft prevention |
| CN111104618A (en) * | 2019-12-19 | 2020-05-05 | 秒针信息技术有限公司 | Webpage skipping method and device |
| CN111385293A (en) * | 2020-03-04 | 2020-07-07 | 腾讯科技（深圳）有限公司 | Network risk detection method and device |
| CN111488452A (en) * | 2019-01-25 | 2020-08-04 | 深信服科技股份有限公司 | Webpage tampering detection method, detection system and related equipment |
| CN111556065A (en) * | 2020-05-08 | 2020-08-18 | 鹏城实验室 | Phishing website detection method and device and computer readable storage medium |
| CN112347402A (en) * | 2020-10-21 | 2021-02-09 | 上海淇玥信息技术有限公司 | Illegal website/APP automatic identification method, system and electronic device |
| CN112711723A (en) * | 2019-10-25 | 2021-04-27 | 北京搜狗科技发展有限公司 | Malicious website detection method and device and electronic equipment |
| CN112866279A (en) * | 2021-02-03 | 2021-05-28 | 恒安嘉新（北京）科技股份公司 | Webpage security detection method, device, equipment and medium |
| CN112989341A (en) * | 2021-03-03 | 2021-06-18 | 中国信息通信研究院 | Method, system and medium for determining fraud-related webpage |
| CN113221035A (en) * | 2021-05-13 | 2021-08-06 | 北京百度网讯科技有限公司 | Method, apparatus, device, medium, and program product for determining an abnormal web page |
| CN113709094A (en) * | 2020-05-22 | 2021-11-26 | 辉达公司 | User-perceptible marking for network address identifiers |
| WO2021253252A1 (en) * | 2020-06-17 | 2021-12-23 | 深圳市欢太数字科技有限公司 | Method and apparatus for testing webpage, and electronic device and storage medium |
| CN114463730A (en) * | 2021-07-15 | 2022-05-10 | 荣耀终端有限公司 | Page identification method and terminal equipment |
| CN114465811A (en) * | 2022-03-09 | 2022-05-10 | 北京华云安信息技术有限公司 | Website login determination method and device, electronic equipment and storage medium |
| CN114760124A (en) * | 2022-04-07 | 2022-07-15 | 黑龙江省敏动传感科技有限公司 | Big data based computer network security intelligent analysis system and method |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101950337A (en) * | 2010-09-08 | 2011-01-19 | 乔永清 | System and method for monitoring website truthful data |
| CN102571768A (en) * | 2011-12-26 | 2012-07-11 | 北京大学 | Detection method for phishing site |
| CN102592067A (en) * | 2011-01-17 | 2012-07-18 | 腾讯科技（深圳）有限公司 | Webpage recognition method, device and system |
| CN102622553A (en) * | 2012-04-24 | 2012-08-01 | 腾讯科技（深圳）有限公司 | Method and device for detecting webpage safety |
| CN102663291A (en) * | 2012-03-23 | 2012-09-12 | 奇智软件（北京）有限公司 | Information prompting method and information prompting device for e-mails |
| CN102819591A (en) * | 2012-08-07 | 2012-12-12 | 北京网康科技有限公司 | Content-based web page classification method and system |
| CN102932348A (en) * | 2012-10-30 | 2013-02-13 | 常州大学 | Real-time detection method and system of phishing website |
| CN103501306A (en) * | 2013-10-23 | 2014-01-08 | 腾讯科技（武汉）有限公司 | Web site identification method, server and system |
| CN103685308A (en) * | 2013-12-25 | 2014-03-26 | 北京奇虎科技有限公司 | Detection method and system of phishing web pages, client and server |
| CN103810193A (en) * | 2012-11-08 | 2014-05-21 | 北京金山安全软件有限公司 | Webpage element shielding method and device |
| CN104809125A (en) * | 2014-01-24 | 2015-07-29 | 腾讯科技（深圳）有限公司 | Method and device for identifying webpage categories |
| CN107018152A (en) * | 2017-05-27 | 2017-08-04 | 北京奇虎科技有限公司 | Message block method, device and electronic equipment |
-
2018
- 2018-05-16 CN CN201810468614.0A patent/CN108683666B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101950337A (en) * | 2010-09-08 | 2011-01-19 | 乔永清 | System and method for monitoring website truthful data |
| CN102592067A (en) * | 2011-01-17 | 2012-07-18 | 腾讯科技（深圳）有限公司 | Webpage recognition method, device and system |
| CN102571768A (en) * | 2011-12-26 | 2012-07-11 | 北京大学 | Detection method for phishing site |
| CN102663291A (en) * | 2012-03-23 | 2012-09-12 | 奇智软件（北京）有限公司 | Information prompting method and information prompting device for e-mails |
| CN102622553A (en) * | 2012-04-24 | 2012-08-01 | 腾讯科技（深圳）有限公司 | Method and device for detecting webpage safety |
| CN102819591A (en) * | 2012-08-07 | 2012-12-12 | 北京网康科技有限公司 | Content-based web page classification method and system |
| CN102932348A (en) * | 2012-10-30 | 2013-02-13 | 常州大学 | Real-time detection method and system of phishing website |
| CN103810193A (en) * | 2012-11-08 | 2014-05-21 | 北京金山安全软件有限公司 | Webpage element shielding method and device |
| CN103501306A (en) * | 2013-10-23 | 2014-01-08 | 腾讯科技（武汉）有限公司 | Web site identification method, server and system |
| CN103685308A (en) * | 2013-12-25 | 2014-03-26 | 北京奇虎科技有限公司 | Detection method and system of phishing web pages, client and server |
| CN104809125A (en) * | 2014-01-24 | 2015-07-29 | 腾讯科技（深圳）有限公司 | Method and device for identifying webpage categories |
| CN107018152A (en) * | 2017-05-27 | 2017-08-04 | 北京奇虎科技有限公司 | Message block method, device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 沙泓州: "面向大规模网络流量的URL实时分类关键技术研究", 《博士学位论文数据库，信息科技辑》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059272A (en) * | 2018-11-02 | 2019-07-26 | 阿里巴巴集团控股有限公司 | A kind of page feature recognition methods and device |
| CN110059272B (en) * | 2018-11-02 | 2023-08-15 | 创新先进技术有限公司 | Page feature recognition method and device |
| CN111488452A (en) * | 2019-01-25 | 2020-08-04 | 深信服科技股份有限公司 | Webpage tampering detection method, detection system and related equipment |
| CN110401660A (en) * | 2019-07-26 | 2019-11-01 | 秒针信息技术有限公司 | Recognition methods, device, processing equipment and the storage medium of false flow |
| CN110401660B (en) * | 2019-07-26 | 2022-03-01 | 秒针信息技术有限公司 | False flow identification method and device, processing equipment and storage medium |
| CN110704867A (en) * | 2019-09-06 | 2020-01-17 | 翼集分电子商务(上海)有限公司 | Method, system, medium and apparatus for integral theft prevention |
| CN110704867B (en) * | 2019-09-06 | 2023-06-16 | 翼集分(上海)数字科技有限公司 | Integral anti-theft method, system, medium and device |
| CN110674442A (en) * | 2019-09-17 | 2020-01-10 | 中国银联股份有限公司 | Page monitoring method, device, equipment and computer readable storage medium |
| CN110674442B (en) * | 2019-09-17 | 2023-08-18 | 中国银联股份有限公司 | Page monitoring method, device, equipment and computer readable storage medium |
| CN112711723B (en) * | 2019-10-25 | 2024-04-30 | 北京搜狗科技发展有限公司 | Malicious website detection method and device and electronic equipment |
| CN112711723A (en) * | 2019-10-25 | 2021-04-27 | 北京搜狗科技发展有限公司 | Malicious website detection method and device and electronic equipment |
| CN111104618A (en) * | 2019-12-19 | 2020-05-05 | 秒针信息技术有限公司 | Webpage skipping method and device |
| CN111385293B (en) * | 2020-03-04 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Network risk detection method and device |
| CN111385293A (en) * | 2020-03-04 | 2020-07-07 | 腾讯科技（深圳）有限公司 | Network risk detection method and device |
| CN111556065A (en) * | 2020-05-08 | 2020-08-18 | 鹏城实验室 | Phishing website detection method and device and computer readable storage medium |
| CN113709094A (en) * | 2020-05-22 | 2021-11-26 | 辉达公司 | User-perceptible marking for network address identifiers |
| WO2021253252A1 (en) * | 2020-06-17 | 2021-12-23 | 深圳市欢太数字科技有限公司 | Method and apparatus for testing webpage, and electronic device and storage medium |
| CN112347402A (en) * | 2020-10-21 | 2021-02-09 | 上海淇玥信息技术有限公司 | Illegal website/APP automatic identification method, system and electronic device |
| CN112866279A (en) * | 2021-02-03 | 2021-05-28 | 恒安嘉新（北京）科技股份公司 | Webpage security detection method, device, equipment and medium |
| CN112866279B (en) * | 2021-02-03 | 2022-12-09 | 恒安嘉新（北京）科技股份公司 | Webpage security detection method, device, equipment and medium |
| CN112989341A (en) * | 2021-03-03 | 2021-06-18 | 中国信息通信研究院 | Method, system and medium for determining fraud-related webpage |
| CN113221035A (en) * | 2021-05-13 | 2021-08-06 | 北京百度网讯科技有限公司 | Method, apparatus, device, medium, and program product for determining an abnormal web page |
| CN114463730A (en) * | 2021-07-15 | 2022-05-10 | 荣耀终端有限公司 | Page identification method and terminal equipment |
| CN114465811B (en) * | 2022-03-09 | 2023-05-23 | 北京华云安信息技术有限公司 | Website login determination method and device, electronic equipment and storage medium |
| CN114465811A (en) * | 2022-03-09 | 2022-05-10 | 北京华云安信息技术有限公司 | Website login determination method and device, electronic equipment and storage medium |
| CN114760124B (en) * | 2022-04-07 | 2022-10-04 | 呀邦管理科技(北京)有限责任公司 | Big data based computer network security intelligent analysis system and method |
| CN114760124A (en) * | 2022-04-07 | 2022-07-15 | 黑龙江省敏动传感科技有限公司 | Big data based computer network security intelligent analysis system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108683666B (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108683666A (en) | A kind of web page identification method and device | |
| US11245718B2 (en) | Method and system for tracking fraudulent activity | |
| CN108156237B (en) | Product information pushing method and device, storage medium and computer equipment | |
| US10121009B2 (en) | Computer system for discovery of vulnerabilities in applications including guided tester paths based on application coverage measures | |
| EP3104294B1 (en) | Fast device classification | |
| CN104092811B (en) | Mobile terminal information download method, system, terminal device and server | |
| CN104468531B (en) | The authorization method of sensitive data, device and system | |
| CN111435507A (en) | Advertisement anti-cheating method and device, electronic equipment and readable storage medium | |
| CN109039987A (en) | A kind of user account login method, device, electronic equipment and storage medium | |
| CN108665297A (en) | Detection method, device, electronic equipment and the storage medium of abnormal access behavior | |
| CN106453216A (en) | Malicious website interception method, malicious website interception device and client | |
| CN102831218B (en) | Method and device for determining data in thermodynamic chart | |
| CN108268635B (en) | Method and apparatus for acquiring data | |
| CN106549959B (en) | Method and device for identifying proxy Internet Protocol (IP) address | |
| CN108696490A (en) | The recognition methods of account permission and device | |
| CN107395558A (en) | For the method for communication, system and computer-readable non-transitory storage medium | |
| CN102833212A (en) | Webpage visitor identity identification method and system | |
| CN106682489A (en) | Password security detection method, password security reminding method and corresponding devices | |
| CN105959371A (en) | Webpage sharing system | |
| CN110912874B (en) | Method and system for effectively identifying machine access behaviors | |
| CN109831429A (en) | A kind of Webshell detection method and device | |
| CN108196829A (en) | A kind of artificial intelligence mobile phone accounting system for analyzing account and method | |
| CN105141610A (en) | Phishing page detection method and system | |
| CN109657459A (en) | Webpage back door detection method, equipment, storage medium and device | |
| CN109672658A (en) | Detection method, device, equipment and the storage medium of JSON abduction loophole |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |