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

A method and system for identifying effective download links based on feature extraction

A feature extraction and identification method technology, applied in the field of information security, can solve problems such as inaccurate identification of download links, achieve efficient calculation and storage tasks, improve security awareness, and be easy to implement

Active Publication Date: 2020-02-21
CENT SOUTH UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problem of inaccurate identification of download links in the prior art, the present invention proposes a method and system for identifying effective download links based on feature extraction

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 and system for identifying effective download links based on feature extraction
  • A method and system for identifying effective download links based on feature extraction
  • A method and system for identifying effective download links based on feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0057] Such as figure 1 and figure 2 As shown, an effective download link identification method based on feature extraction includes the following steps:

[0058] Step 1: Obtain the link training data from the cloud server, and extract the link data feature vector from the training data;

[0059] Step 2: In the cloud server, train a machine learning discriminator based on link data feature vectors and link labels;

[0060] The linked data feature vectors include at least the following:

[0061] 1) Whether the URL contains "@", if so, the characteristic value is 1, otherwise it is 0;

[0062] 2) Whether there are more than 5 "." in the URL, if so, the characteristic value is 1, otherwise it is 0;

[0063] 3) Whether the URL is an IP address, if it is an IP address, the characteristic value is 1, otherwise it is 0;

[0064] 4) Whether the URL resourc...

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 method and system for identifying effective download links based on feature extraction. The method includes the following steps: Step 1: Obtain link training data from a cloud server, and extract link data feature vectors from the training data; Step 2: In the In the cloud server, train the machine learning discriminator based on the link data feature vector and the link label; Step 3: extract the link data feature vector from the link to be identified according to the method of step 1, input it into the machine learning discriminator obtained in step 2, and output the link label to complete the identification of the link. Compared with the existing technology, this scheme provides an active identification mechanism to overcome the missed judgment caused by pure blacklist comparison; it proposes personalized features to make up for the difference in identification targets; the client uses plug-ins and pop-up results The form of feedback is realized to enhance interactivity and user experience; (4) Relying on the cloud computing architecture, the burden on the user's computer is greatly reduced and management costs are saved.

Description

technical field [0001] The invention belongs to the field of information security, in particular to a method and system for identifying effective download links based on feature extraction. Background technique [0002] The Internet has brought great convenience to people's production and life, but at the same time, the development of the Internet has also brought many problems. Some virus software and malicious code spread wildly through the "shortcut" of the Internet, seriously threatening people's information and property safety. Sometimes when downloading a certain file, especially when going to some small download sites to download, it is found that the downloaded download link is not the desired file, but a promotional advertisement with a commercial nature, and some are vulgar, unsightly, Pornographic websites that seriously affect the physical and mental health of minors. What's more, some links will download rogue software or Trojan horses in the background, which ...

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): H04L29/08H04L29/06G06F16/955G06K9/62G06N99/00
CPCH04L63/0236H04L63/1466H04L67/1097G06F16/9558G06N20/00G06F18/214
Inventor 申卓祥覃涛明段桂华李智
Owner CENT SOUTH UNIV