Unlock instant, AI-driven research and patent intelligence for your innovation.

A Web Page Anomaly Detection Method Based on Online Classification

An anomaly detection and web page technology, which is applied in network data retrieval, text database clustering/classification, website content management, etc. Scientific and reasonable effect of detection performance and accuracy, gradient direction

Active Publication Date: 2020-02-14
ANHUI UNIVERSITY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Traditional classification learning methods, such as SVM and Adaboost algorithms, need to transfer all training data into memory for processing in actual implementation. The huge amount of data and limited application environment have become the main constraints of traditional classification learning methods, which cannot meet the needs of massive web pages in the Internet age. data needs

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 Web Page Anomaly Detection Method Based on Online Classification
  • A Web Page Anomaly Detection Method Based on Online Classification
  • A Web Page Anomaly Detection Method Based on Online Classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In this embodiment, a webpage anomaly detection method based on online classification includes an online webpage classification model training step and a webpage anomaly detection step, specifically, as figure 1 As shown, proceed as follows:

[0045] Step 1: Online web page classification model training:

[0046] Step 1.1: Collect the source code data of T webpages as T webpage samples, and use regular expressions to extract the attribute characteristics of abnormal webpages in T webpage samples, and obtain the sample data of T webpage samples, common attribute characteristics such as Document. The number of occurrences of write(), the number of occurrences of Exe, the number of occurrences of Usescape, super long strings, iframe / frame frames, etc., through the analysis of abnormal web pages, compared with normal web pages, they often show abnormalities of the above attributes; among them, the tth web page sample The sample data of , denoted as (x t ,y t ),And a: I...

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 webpage exception detection method based on online classification. The method comprises the following steps that: S1: inputting webpage training data; S2: preprocessing the webpage training sample data; and S3: training an online webpage classification model. Exceptional webpage detection classification comprises the following steps that: S4: inputting webpage sample datato be detected; S5: preprocessing the webpage sample data to be detected; and S6: through the online webpage classification model, classifying the webpage sample data to be detected, and detecting whether the webpage sample data to be detected is an exceptional webpage or not. By use of the method, the exceptional webpage can be quickly detected from mass unbalanced webpage data, and network safety and Internet user experience are improved.

Description

technical field [0001] The invention relates to the technical field of statistical learning classification, in particular to an online classification-based abnormality detection method for web pages. Background technique [0002] In recent years, with the popularization of the Internet, the number of new webpages has increased exponentially every day. It has become an important means for people to obtain information, and the abnormal webpages that follow have gradually become one of the main threats to network information security. Using the advantages of online classification algorithms to effectively detect abnormal web pages, especially for timely anomaly detection and identification of newly emerging web page samples, is the main content of current research in the field of web security detection, and it is also an important issue to improve user experience. [0003] Among the massive webpages, the number of abnormal webpages is very small, so how to accurately identify t...

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): G06F16/35G06F16/958
CPCG06F16/35G06F16/958
Inventor 程凡章霞张闯
Owner ANHUI UNIVERSITY