CN115033819A - Internet risk monitoring method and system - Google Patents
Internet risk monitoring method and system Download PDFInfo
- Publication number
- CN115033819A CN115033819A CN202210447217.1A CN202210447217A CN115033819A CN 115033819 A CN115033819 A CN 115033819A CN 202210447217 A CN202210447217 A CN 202210447217A CN 115033819 A CN115033819 A CN 115033819A
- Authority
- CN
- China
- Prior art keywords
- website
- auditing
- screenshot
- link
- search
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9558—Details of hyperlinks; Management of linked annotations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an internet risk monitoring method and system, wherein the method comprises the following steps: s1, initiating a simulated search to search a target advertisement delivery website; s2, acquiring a search result list of a search engine, and acquiring link information in the search result list; s3 using the acquired link information and acquiring further jump links until acquiring final jump links; s4, acquiring at least one of the website screenshot, the website code and the website text content of the final jump link; and S5, auditing by adopting a preset auditing strategy based on an artificial intelligence technology according to at least one of the acquired website screenshot, the website code and the website text content to obtain a website risk auditing result. The invention is beneficial to improving the reliability and the intelligent level of the supervision of the advertisement delivery website.
Description
Technical Field
The invention relates to the technical field of internet, in particular to an internet risk monitoring method and system.
Background
At present, all agents of online advertisements need to carry out risk control on online advertisement websites or pages operated by the agents, firstly, the websites are prevented from generating illegal information due to network attack, and secondly, the websites provider is prevented from intentionally tampering the websites to generate illegal information.
The prior art can only directly monitor the website or the webpage, has no way to process the skip of the website under the condition of judging time, from which search engine and region, has insufficient monitoring strength, and cannot effectively prevent illegal information.
Com, for example, a web site is a paid search advertisement and a search keyword is a tooling, the content of the web site is legally compliant most of the time, but when the web site is tooled through the search keyword die at night, another online lottery web site is accessed by clicking the promotional link. Because the website does the code jump, when the website judges that the website is in the night and comes from a certain search engine, the website jumps to another website.
Disclosure of Invention
The invention aims to provide an internet risk monitoring method and system aiming at the problem that the online advertising website or webpage monitoring is not enough and illegal information cannot be effectively prevented.
The purpose of the invention is realized by adopting the following technical scheme:
in a first aspect, the present invention provides an internet risk monitoring method, including:
s1, initiating a simulated search to search a target advertisement delivery website;
s2, obtaining a search result list of a search engine, and obtaining link information in the search result list;
s3 using the acquired link information and acquiring further jump links until acquiring final jump links;
s4, acquiring at least one of the website screenshot, the website code and the website text content of the final jump link;
s5, according to at least one of the obtained website screenshot, the website code and the website text content, auditing by adopting a preset auditing strategy based on an artificial intelligence technology to obtain a website risk auditing result.
In one embodiment, step S1 includes: and initiating simulation retrieval according to the preset target advertisement delivery website information and the preset patrol frequency information, and searching the target advertisement delivery website in a search engine.
In one embodiment, in step S2, when the obtained search result list does not include a direct link, a jump link of the search engine is obtained as link information in the list in the search result through text matching.
In one embodiment, in step S3, the website is accessed using the acquired link information, and if the website is not jumped, the link of the website is used as the final jumped link; if a jump occurs, the jump link is further accessed until the final jump link is obtained.
In one embodiment, in step S5, the performing an audit according to the obtained screenshot of the website, the website code, and the text content of the website includes: image auditing, text auditing and keyword auditing; wherein
The image checking comprises the steps of comparing the current screenshot of the website with the screenshot during registration by using an image similarity algorithm, and if the similarity difference is higher than a threshold value, outputting an image checking result to fail;
the text auditing comprises the steps of comparing the current text of the website with the text during registration, and if the similarity difference is higher than a threshold value, outputting a text auditing result and not passing;
and the keyword audit comprises the collision comparison of a self-defined keyword library, and if the number of the illegal keywords is higher than a threshold value, the keyword audit result is output and is not passed.
In one embodiment, step S5 further includes:
and when one of the image audit result, the text audit result and the keyword audit result is not passed, outputting a website risk audit result which is not passed, and sending an alarm notice.
In one embodiment, in step S5, the image review further includes accessing an online AI analysis engine to perform review, and the AI analysis engine analyzes whether the screenshot of the website includes gambling, violence, and pornographic image information, so as to obtain a website image review result.
In a second aspect, the present invention provides an internet risk monitoring system, which is configured to implement the internet risk monitoring method according to any one of the embodiments of the first aspect.
The beneficial effects of the invention are as follows: through the simulation of the search engine, the monitored webpage considers that the current click is from the click through the search engine, so that the internal processing logic of the webpage is triggered, and if the webpage has malicious jump, the jumped webpage can be further obtained. And (3) carrying out 3-item monitoring (image auditing, text auditing and keyword auditing) on the final webpage, and triggering an alarm notification once the monitoring is higher than a set threshold value. The method is beneficial to improving the reliability and the intelligent level of supervision of the advertisement delivery website.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
Fig. 1 is a schematic flow chart of an internet risk monitoring method according to the present invention.
Fig. 2 is a schematic diagram of a framework of an internet risk monitoring method according to the present invention.
Detailed Description
The invention is further described in connection with the following application scenarios.
Referring to fig. 1 and 2, an internet risk monitoring method is shown, which includes:
s1, initiating a simulated search to search a target advertisement delivery website;
in one embodiment, step S1 includes: and initiating simulation retrieval according to the preset target advertisement delivery website information and the preset patrol frequency information, and searching the target advertisement delivery website in a search engine.
Before step S1, the method further includes setting a monitoring website polling list and a polling frequency of a corresponding website, so that the system can automatically complete polling monitoring and risk monitoring of the websites in the training list.
S2, acquiring a search result list of a search engine, and acquiring link information in the search result list;
in one embodiment, in step S2, when the obtained search result list does not include a direct link, a jump link of the search engine is obtained as link information in the list in the search result through text matching.
The method comprises the steps of obtaining a search result list of a search engine, wherein the list does not necessarily contain direct links, and possibly can be a text display of a released website, and obtaining jump links of the search engine through text matching. Example (c): com/link is search id.
S3 using the acquired link information and acquiring further jump links until acquiring final jump links;
in one embodiment, in step S3, the obtained link information is used to access a website, and if the website is not jumped, the link of the website is used as a final jumped link; if a jump occurs, the jump link is further accessed until the final jump link is obtained. The final jump page is accessed by always tracking the webpage jump, so that malicious jump can be effectively prevented, and the adaptability of webpage risk monitoring is improved.
In one scenario, in order to further reduce misjudgment in the jump link jump access process, a jump link ignore list for setting a website can be modified in the jump access process, and if the website frequently jumps to a trusted website, such as an official electric commerce flagship store, misjudgment is reduced in an increase ignoring mode.
S4, acquiring at least one of the website screenshot, the website code and the website text content of the final jump link;
sending the website screenshot, the website code and the website text content to an auditing module, and completing further auditing steps by the auditing module;
and S5, auditing by adopting a preset auditing strategy based on an artificial intelligence technology according to at least one of the acquired website screenshot, the website code and the website text content to obtain a website risk auditing result.
In one embodiment, in step S5, the performing an audit according to the obtained screenshot of the website, the website code, and the text content of the website includes: image auditing, text auditing and keyword auditing; wherein
The image checking comprises the steps that the current screenshot of the website is compared with the screenshot during registration by using an image similarity algorithm, if the similarity difference is higher than a threshold value, an image checking result is output and a warning is triggered;
in one scene, before image review is performed, a standard screenshot A in a normal (trusted) state is generated for each website, a current screenshot is generated during daily inspection, image similarity calculation is performed on the screenshot A and the standard screenshot A, and an alarm is given out if the similarity is lower than a set threshold;
in a scenario, calculating picture similarity between a current screenshot and a standard screenshot A, comprising:
the similarity value of the two screenshots is obtained by calculating the Euclidean distance between the current screenshot and the standard screenshot A, wherein the Euclidean distance calculation function is as follows:
where d (A, B) represents the Euclidean distance between the standard screenshot A and the current screenshot B, where a i Characteristic value (e.g. pixel value of pixel point), b, representing the ith element in the standard screenshot i The feature value (e.g., pixel value of a pixel point) of the ith element in the current screenshot is shown, where n represents the total number of elements (pixel points).
In another scenario, calculating the picture similarity between the current screenshot and the standard screenshot A includes:
the similarity value of the two screenshots is obtained by calculating the cosine distance between the current screenshot and the standard screenshot A, wherein the cosine distance calculation function is as follows:
where cos θ represents the cosine distance between the standard screenshot A and the current screenshot B, where a i Characteristic value (e.g. pixel value of pixel point), b, representing the ith element in the standard screenshot i The feature value (e.g., pixel value of pixel) of the ith element in the current screenshot is shown, where n represents the total number of elements (pixels).
In another scenario, calculating the picture similarity between the current screenshot and the standard screenshot A includes:
the similarity values of the two screenshots are obtained by combining and calculating the Euclidean distance and the cosine distance of the current screenshot and the standard screenshot A, wherein the similarity value calculation function is as follows:
Y(A,B)＝ω 1 ×d(A,B)+ω 2 ×cosθ
in the formula, Y (A, B) represents the similarity value of the standard screenshot A and the current screenshot B, d (A, B) represents the Euclidean distance between the standard screenshot A and the current screenshot B, cos theta represents the cosine distance between the standard screenshot A and the current screenshot B, and omega represents the distance between the standard screenshot A and the current screenshot B 1 And ω 2 Respectively, represent the set normalized weight factors.
According to the embodiment, a similarity value calculation mode aiming at the standard screenshot and the current screenshot is provided, so that the similarity between the two screenshots can be accurately reflected, and the abnormal condition of the current website screenshot can be effectively judged.
In one scene, comparing the current screenshot of the website with the screenshot during registration through a similarity measurement algorithm, wherein the adopted similarity calculation method comprises the steps of adopting one or more of an average hash algorithm, a perception hash algorithm, a difference hash algorithm, a deep learning method and the like to detect the similarity of the two screenshots, and if the similarity difference between the two screenshots is higher than a set threshold value, outputting an image verification result and not passing, and triggering warning;
in one embodiment, in step S5, the image review further includes accessing an online AI analysis engine to perform review, and the AI analysis engine analyzes whether the screenshot of the website includes gambling, violence, and pornographic image information, so as to obtain a website image review result.
In one scenario, the image review further comprises the steps of reviewing the current website screenshot by adopting an AI analysis engine, analyzing whether illegal pictures (such as pornographic pictures, bloody smell pictures and the like) exist in the image, and if the illegal pictures are found, outputting an image review result, failing to pass, and triggering warning; the picture of the current website is intelligently analyzed through the AI analysis engine, so that violation information hidden in the picture can be further found, and the reliability of webpage risk monitoring can be improved.
The AI analysis engine can be switched autonomously according to actual conditions, and the threshold value for judging the harmful information is adjusted at any time, so that the balance between safety and efficiency is achieved. In one scenario, for different AI analysis engines, an analysis strategy is set, the analysis strategy is provided with corresponding effective dates and can be switched at any time, the AI analysis engine outputs corresponding judgment values (normalized judgment values) for various harmful information according to the analysis strategy, wherein each analysis strategy is provided with a corresponding judgment threshold, the judgment threshold comprises two sections including a suspected section and an illegal section, for example, a pornographic judgment is that the suspected (0.7-0.9) illegal section (0.9-1), and when the judgment values fall into different sections, an alarm behavior corresponding to the sections is triggered (different sections can be correspondingly set with different alarm behaviors).
The AI analysis engine may be an artificial intelligence engine provided by Baidu cloud, Aliyun, or other trained artificial intelligence engine, and can be freely called through a provider interface, and in an actual operation process, the AI interface can be dynamically changed according to a monitoring result to call a corresponding AI analysis engine, where a data format returned through the AI interface is general, for example: { contraband category (pornography, gambling), contraband indicator (category, reason of contraband), treatment outcome (suspected, violation) }.
The manager can freely switch the proper AI analysis engines to complete the examination of the website pictures according to the performance and accuracy of each AI analysis engine. The method helps balance the sensitivity and accuracy of the audit according to actual conditions.
In a scene, a system respectively calls an artificial intelligence engine provided by Baidu cloud and an artificial intelligence engine provided by Aliyun to perform image verification on a current website screenshot (or training data) in a background mode, a manager can freely switch a supplier interface according to the requirement or the analysis accuracy of the two, and calls the artificial intelligence engine provided by a supplier with high accuracy to complete an image verification task.
The text auditing comprises the steps of comparing the current text of the website with the text during registration, and if the similarity difference is higher than a threshold value, outputting a text auditing result, failing to pass and triggering warning;
and the keyword audit comprises the collision comparison of a self-defined keyword library, and if the number of the illegal keywords is higher than a threshold value, the keyword audit result is output and is not passed, and a warning is triggered.
The keyword library may be customized, for example, if a hundred-degree advertisement is delivered, a hundred-degree violation keyword library is added, for example: the system comprises billing, cigarettes, chess and cards and the like so as to meet the monitoring requirements under a search engine.
When (before) keyword verification, corresponding rule files can be imported according to different advertisers (such as Baidu, Ali, byte jumping and the like), an illegal keyword library can be intelligently extracted according to the rule files, keyword verification is carried out on the website text content based on the extracted illegal keyword library, if the illegal keywords exist, a keyword verification result is output and a warning is triggered if the illegal keywords do not pass.
In one scenario, rule files corresponding to different advertisers are stored in a system, corresponding advertisers can be automatically or manually selected according to the advertisers where different target websites are located, the system further refers to the corresponding rule files according to the selected advertisers, corresponding keyword libraries are extracted from the rule files, keyword verification is carried out on current webpage content according to the extracted keyword libraries, and corresponding keyword verification results are obtained; corresponding keyword management rules can be set according to different advertisers, and the adaptability of the system is improved.
The manner of triggering the warning includes sending an alarm message to an administrator (patrol administrator), where the manner of sending the alarm message includes public number by WeChat, short message, telephone (synthesized voice), etc., and meanwhile, a corresponding reminding manner is started for a time slot, for example, a manner of using the telephone at night prevents the patrol administrator from not receiving the relevant alarm message.
In one embodiment, step S5 further includes:
and when one of the image audit result, the text audit result and the keyword audit result is not passed, outputting a website risk audit result which is not passed, and sending an alarm notice.
And when one of the image audit result, the text audit result and the keyword audit result is passed, judging that the currently monitored website has risks, namely the system quits the audit of the website and starts the audit of the next website.
Meanwhile, the system can also judge the risk threshold of the website (webpage) according to the image audit result, the text audit result and the keyword audit result through an audit strategy set in advance, and if the risk threshold is higher than the set threshold, a risk notification is sent.
The system can set a daily patrol and manual patrol mode, and in the daily patrol mode, the system initiates automatic patrol aiming at target search results and advertisement delivery websites at set time periods; in addition, patrol can be initiated manually according to actual conditions, and the method can be suitable for use in different scenes.
In one scenario, according to the obtained website risk audit result, corresponding website risk audit result text information can be pushed to a manager or the manager is notified in a smart phone mode, and the manager can process the corresponding abnormal website at the first time.
In the above embodiment, through simulation of the search engine, the monitored webpage is made to assume that the current click is a click from the search engine, so as to trigger the internal processing logic of the webpage, and if the webpage has malicious jump, the jumped webpage can be further obtained. And (3) carrying out 3-item monitoring (image auditing, text auditing and keyword auditing) on the final webpage, and triggering an alarm notification once the monitoring is higher than a set threshold value.
The keyword library can be customized, for example, if a hundred degree advertisement is put, a hundred degree violation keyword library is added, such as: billing, cigarettes, chess and cards, and the like.
Meanwhile, the keyword library can be automatically set according to the imported rule file by importing the corresponding rule file, and the operation is convenient.
Meanwhile, based on the internet risk monitoring method, the present invention further provides an internet risk monitoring system, which is used for implementing the method steps of any one of the embodiments of the internet risk monitoring method shown in fig. 1, and the description of the present invention is not repeated here.
It is to be noted that, through the above description of the embodiments, it is clear for those skilled in the art that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For a hardware implementation, the processor may be implemented in one or more of the following units: an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof. For a software implementation, some or all of the procedures of an embodiment may be performed by a computer program instructing associated hardware. In practice, the program may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. Computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be analyzed by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (9)
1. An internet risk monitoring method, comprising:
s1, initiating a simulated search to search a target advertisement delivery website;
s2, acquiring a search result list of a search engine, and acquiring link information in the search result list;
s3 using the acquired link information and acquiring further jump links until acquiring final jump links;
s4, acquiring at least one of the website screenshot, the website code and the website text content of the final jump link;
s5, according to at least one of the obtained website screenshot, the website code and the website text content, auditing by adopting a preset auditing strategy based on an artificial intelligence technology to obtain a website risk auditing result.
2. The internet risk monitoring method of claim 1, wherein step S1 includes: and initiating simulation retrieval according to the preset target advertisement delivery website information and the preset patrol frequency information, and searching the target advertisement delivery website in a search engine.
3. The internet risk monitoring method of claim 1, wherein in step S2, when the obtained search result list does not include a direct link, a jump link of the search engine is obtained as link information in the list in the search result through text matching.
4. The internet risk monitoring method according to claim 1, wherein in step S3, the obtained link information is used to access a website, and if the website has not jumped, the link of the website is used as a final jumped link; if a jump occurs, the jump link is further accessed until the final jump link is obtained.
5. The internet risk monitoring method according to claim 1, wherein in step S5, the auditing according to the obtained screenshot of the website, the website code and the text content of the website includes: image auditing, text auditing and keyword auditing; wherein
The image checking comprises the steps of comparing the current screenshot of the website with the screenshot during registration by using an image similarity algorithm, and if the similarity difference is higher than a threshold value, outputting an image checking result to be failed;
the text auditing comprises the steps of comparing the current text of the website with the text during registration, and if the similarity difference is higher than a threshold value, outputting a text auditing result and not passing;
and the keyword audit comprises the collision comparison of a self-defined keyword library, and if the number of the illegal keywords is higher than a threshold value, the keyword audit result is output and is not passed.
6. The internet risk monitoring method of claim 5, wherein step S5 further comprises:
and when one of the image audit, the text audit and the keyword audit does not pass, outputting a website risk audit result, and sending an alarm notice.
7. The internet risk monitoring method of claim 5, wherein the image review in step S5 further includes accessing an online AI analysis engine for review, and the AI analysis engine analyzes whether the website screenshot includes gambling, violence, and pornography image information to obtain a website image review result.
8. The internet risk monitoring method of claim 7, wherein the AI analysis engine can switch autonomously according to actual conditions; aiming at different AI analysis engines, an analysis strategy is set, the AI analysis engines output corresponding judgment values aiming at various harmful information according to the analysis strategy, and when the judgment values fall into different intervals, alarm behaviors corresponding to the intervals are triggered.
9. An internet risk monitoring system for implementing an internet risk monitoring method as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210447217.1A CN115033819A (en) | 2022-04-26 | 2022-04-26 | Internet risk monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210447217.1A CN115033819A (en) | 2022-04-26 | 2022-04-26 | Internet risk monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115033819A true CN115033819A (en) | 2022-09-09 |
Family
ID=83118742
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210447217.1A Pending CN115033819A (en) | 2022-04-26 | 2022-04-26 | Internet risk monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115033819A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120054669A1 (en) * | 2010-08-31 | 2012-03-01 | Net-Express, Ltd. | Method and system for providing enhanced user interfaces for web browsing |
| CN102902722A (en) * | 2012-09-04 | 2013-01-30 | 北京奇虎科技有限公司 | Method and system for treating information safety |
| CN107786537A (en) * | 2017-09-19 | 2018-03-09 | 杭州安恒信息技术有限公司 | A kind of lonely page implantation attack detection method based on internet intersection search |
| CN113886730A (en) * | 2021-09-25 | 2022-01-04 | 北京天融信网络安全技术有限公司 | Dark chain detection method and system based on link content |
-
2022
- 2022-04-26 CN CN202210447217.1A patent/CN115033819A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120054669A1 (en) * | 2010-08-31 | 2012-03-01 | Net-Express, Ltd. | Method and system for providing enhanced user interfaces for web browsing |
| CN102902722A (en) * | 2012-09-04 | 2013-01-30 | 北京奇虎科技有限公司 | Method and system for treating information safety |
| CN107786537A (en) * | 2017-09-19 | 2018-03-09 | 杭州安恒信息技术有限公司 | A kind of lonely page implantation attack detection method based on internet intersection search |
| CN113886730A (en) * | 2021-09-25 | 2022-01-04 | 北京天融信网络安全技术有限公司 | Dark chain detection method and system based on link content |
Non-Patent Citations (1)
| Title |
|---|
| 游闽键, 知识产权出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241461B (en) | User portrait construction method and device | |
| US9621566B2 (en) | System and method for detecting phishing webpages | |
| US20190122258A1 (en) | Detection system for identifying abuse and fraud using artificial intelligence across a peer-to-peer distributed content or payment networks | |
| CN111401416B (en) | Abnormal website identification method and device and abnormal countermeasure identification method | |
| CN110413908A (en) | The method and apparatus classified based on web site contents to uniform resource locator | |
| CN103685307A (en) | Method, system, client and server for detecting phishing fraud webpage based on feature library | |
| US9871826B1 (en) | Sensor based rules for responding to malicious activity | |
| CN111738770B (en) | Advertisement abnormal flow detection method and device | |
| Ramesh et al. | Identification of phishing webpages and its target domains by analyzing the feign relationship | |
| CN105335869A (en) | Early warning method and system for advertisement monitoring | |
| CN111859234A (en) | Illegal content identification method and device, electronic equipment and storage medium | |
| CN112347327A (en) | Website detection method and device, readable storage medium and computer equipment | |
| CN112532624B (en) | Black chain detection method and device, electronic equipment and readable storage medium | |
| CN109413016A (en) | A kind of rule-based message detecting method and device | |
| CN110796053A (en) | Video detection method and device, electronic equipment and computer readable storage medium | |
| CN114693192A (en) | Wind control decision method and device, computer equipment and storage medium | |
| CN114157568B (en) | Browser secure access method, device, equipment and storage medium | |
| CN115080956A (en) | Detection method and system based on violation permission of installed application program of mobile terminal | |
| KR102159399B1 (en) | Device for monitoring web server and analysing malicious code | |
| Clasen et al. | Friend or foe: An investigation into recipient identification of sms-based phishing | |
| CN112307464A (en) | Fraud identification method and device and electronic equipment | |
| CN108804501A (en) | A kind of method and device of detection effective information | |
| CN111131166B (en) | User behavior prejudging method and related equipment | |
| CN115659351B (en) | Information security analysis method, system and equipment based on big data office | |
| CN111563765A (en) | Cheating user screening method, device and equipment and readable storage medium |
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 |