Supercharge Your Innovation With Domain-Expert AI Agents!

Construction method of multi-type abnormal webpage classification model and abnormal webpage detection method

A webpage classification and multi-type technology, applied in genetic models, network data retrieval, genetic rules, etc., can solve the problems of not considering the classification accuracy, not taking into account the problem that the webpage sample data contains different attribute characteristics, etc.

Pending Publication Date: 2020-11-20
XIDIAN UNIV
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Traditional webpage classification algorithms, such as decision tree classification algorithm and naive Bayesian algorithm, do not consider the problem that webpage sample data contains different attribute characteristics, and their performance has great limitations
At the same time, traditional classification learning methods, such as the SVM algorithm, do not take into account the problem of classification accuracy in actual implementation

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
  • Construction method of multi-type abnormal webpage classification model and abnormal webpage detection method
  • Construction method of multi-type abnormal webpage classification model and abnormal webpage detection method
  • Construction method of multi-type abnormal webpage classification model and abnormal webpage detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] This embodiment provides a multi-type abnormal web page classification model, which is constructed according to the following method, including the following steps:

[0039] Step 1: Divide abnormal webpages into offensive malicious webpages, induced fraudulent webpages, and spam webpages according to the attack means or attack targets of the abnormal webpages;

[0040] Step 1.1: Classify abnormal webpages into attacking malicious webpages, inducing fraudulent webpages and spam webpages. Among them, attacking webpages that will cause the user's computer to download malicious programs, performance degradation, damage to the computer operating system, or even directly cause damage to computer hardware are defined as offensive malicious webpages, which will gain user trust through camouflage, temptation, etc., and then Malicious webpages that induce users to enter their private information or even transfer money directly are defined as inducing fraudulent webpages, which wi...

Embodiment 2

[0073] This embodiment provides a web page anomaly detection method, which is implemented according to the following steps:

[0074] Step 1. Using the method described in Embodiment 1 to construct a multi-type abnormal web page classification model:

[0075] Step 2. Persist the multi-type abnormal web page classification model into the text Text;

[0076] Step 3, input the URL of the webpage to be detected, obtain the attribute vector of the webpage to be detected according to the method described in embodiment 1;

[0077] Wherein, the URL of the webpage to be detected is input as the sample to be tested, and the relevant attribute features of the abnormal webpage are extracted according to the method in step 1 and the attribute vector x is obtained, denoted as x=(μ 1 ,μ 2 ,...,μ t ), where μ i Indicates the attribute of the i-th abnormal web page in the sample to be tested;

[0078] Step 4. Input the attribute vector of the webpage to be detected obtained in step 3 into ...

Embodiment 3

[0081] This embodiment provides a multi-type abnormal webpage detection method, including two major steps: an online webpage classification model training step and a webpage anomaly detection step, specifically, as figure 1 As shown, proceed as follows:

[0082] Step 1: Construction and training of multi-type abnormal web page classification model:

[0083]Step 1: Attack webpages that will cause the user's computer to download malicious programs, performance degradation, computer operating system damage, or even directly cause damage to computer hardware are classified as offensive malicious webpages, which will gain user trust through camouflage, temptation, etc. Malicious webpages that induce users to enter their private information or even transfer money directly are classified as induced fraudulent webpages, which will be distributed in advertising pages, comment pages, email links, and SMS links of major websites in various ways, without nutrition. Abnormal webpages that...

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 discloses a construction method of a multi-type abnormal webpage classification model and an abnormal webpage detection method. The construction method of the multi-type abnormal webpageclassification model comprises the following steps of: classifying abnormal web pages of different types; selecting corresponding attributes according to attack intentions and means of different types of webpages; selecting the most appropriate optimal attribute through SVM-RFE (Support Vector Machine-Restriction Fragment Element); taking the accuracy of each attribute on the naive Bayesian as afeature validity, introducing the feature validity into an SVM (Support Vector Machine), designing a support vector machine with the feature validity, and training the selected features in a support vector machine containing the feature validity to obtain a multi-type abnormal webpage classification model. The abnormal webpage detection method comprises the following steps: detecting abnormal webpages; and extracting abnormal features from the submitted URLs, carrying out standardization processing, and then calling the multi-type abnormal webpage classification model to carry out detection.

Description

technical field [0001] The invention belongs to the technical field of statistical learning classification, in particular to a multi-type anomaly detection method. Background technique [0002] Whether it is a national government agency, or an enterprise, school, or institution, all need a website to promote, introduce themselves, and release information for themselves. With the development of the information age, people's daily needs such as shopping, eating and taking taxis can be fulfilled through the Internet, which not only facilitates people's lives, but also saves a lot of manpower and financial resources. However, while normal websites provide people with information, entertainment and convenience, they also allow criminals to see business opportunities, and abnormal websites are becoming more and more proliferating and diverse. It is difficult to identify the difference between abnormal webpages and normal webpages with ordinary network names, and it is particularl...

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
IPC IPC(8): G06K9/62G06N3/12G06F16/955
CPCG06N3/126G06F16/9566G06F18/2411G06F18/24155
Inventor 陆毛毛权义宁苗启广宋建锋戚玉涛谢琨孙鹏岗
Owner XIDIAN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com