A method, apparatus and system for securing a website through machine learning

A machine learning and protection device technology, applied in the field of network security, to achieve the effect of improving accuracy and comprehensiveness, and reducing the time of machine learning

Active Publication Date: 2020-12-18
ZHONGYUNWANGAN TECHNOLOGY (BEIJING) CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, provide an efficient and intelligent method of protecting websites from unknown attacks, solve the different characteristics of each website, and users' different access habits for each website, through machine The learning method quickly establishes a new website access model for each website visit, without additional labor costs and maintenance time, reducing the deployment cost of security protection and saving construction time

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method, apparatus and system for securing a website through machine learning
  • A method, apparatus and system for securing a website through machine learning
  • A method, apparatus and system for securing a website through machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] Such as figure 1 As shown, the method for machine learning protection website described in this embodiment includes the following steps:

[0072] S101, switch to a passive mode, and establish a reverse proxy connection with the website to receive an access request to the website;

[0073] The website protection device is switched to passive mode, set between the website server and the user access end, receives the access request from the user end and then sends the request to the website server end, and sends the return result of the data from the server end to the user access request end. The website protection device uses the homepage of the website, that is, the root directory, as the entry point for machine learning.

[0074] S102. Send an alarm message to the administrator according to the threatening access request;

[0075] The website protection device protects the website in the form of a reverse proxy. A large number of users monitor the access methods and ...

Embodiment 2

[0090] The method for protecting a website through machine learning provided in this embodiment is used to quickly and accurately update the website security model after the website is updated. Described method specifically comprises the following steps:

[0091] S201, switch to passive mode, and establish a reverse proxy connection with the website to receive an access request to the website;

[0092] S202. Send an alarm message to the administrator according to the threatening access request;

[0093] S203. The administrator judges whether the access request corresponding to the alarm information is released, and if so, adds a release rule;

[0094] S204. Repeat S202 and S203 until all services of the website are accessed, and learn the release rules to establish a website security model.

[0095] S205. Switch to the active mode, and judge whether the access request conforms to the website security model, and if so, allow access to the website.

[0096] When switching to ...

Embodiment 3

[0103] Such as image 3 As shown, a website protection device 300 using the above machine learning method for protecting websites includes a receiving access request module 301, an alarm prompt module 302, a judging module 303, and a machine learning module 304;

[0104] The receiving access request module 301 is used to establish a reverse proxy connection with the website; wherein, setting up the reverse proxy connection is specifically to receive the access request module 301 to read the website homepage, and access all services of the website through the website homepage to receive visits to the website ask;

[0105] The warning prompt module 302 is used to send warning information for all threatening access requests; where the threatening visits are other access requests except for the visits to the website home page and the links in the web pages;

[0106] After the alarm prompt module 302 and the judgment module 303 establish release rules for all services of the websi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a method for protecting a website through machine learning. A website security model protection website is established through the machine learning. The method comprises the following steps: establishing a reverse proxy connection with the website by a website protection apparatus to receive an access request of the website, and sending alarm information of the access request; judging whether the alarm information corresponding to the access request is released, and if so, adding a release rule; and establishing a website security model of the specific website according to the release rule, and intercepting access with threats by the website protection apparatus according to the website security model. The technical scheme provided by the invention can securely protect website, education, e-commerce, bank and other information systems based on Web. The unknown attacks can be effectively prevented, thereby reducing the maintenance personnel and the maintenance cost and reducing the enterprise cost.

Description

technical field [0001] The invention belongs to the field of network security, and in particular relates to a method for machine learning to protect a website. Background technique [0002] With the rapid development of the Internet, website security issues have become prominent. Website applications often carry main business functions and store a large amount of valuable data. Traditional website firewalls use signature databases to protect websites and cannot defend against unknown threats. There are more and more attacks against web servers and databases, such as attacks against SQL injection vulnerabilities in databases, or attacks against server ports. Due to the diversity and complexity of websites, there are thousands of differences, and artificial methods cannot fully learn the content of websites. [0003] One of the existing technologies mainly adopts the matching based on blacklist feature library to protect the website, and all access requests that do not meet ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): H04L29/06G06N20/00
CPCG06N20/00H04L63/0263H04L63/1441
Inventor 王茁
Owner ZHONGYUNWANGAN TECHNOLOGY (BEIJING) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap