Hierarchical phishing website detection method based on deep learning

A technology for phishing websites and detection methods, applied in biological neural network models, instruments, character and pattern recognition, etc., can solve problems such as reducing generalization ability, achieve real-time detection, high accuracy, and avoid manual feature design.

Active Publication Date: 2019-12-20
SUN YAT SEN UNIV
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The problem with this patent is that its classifier is obtained by extracting fixed features from URLs and web page content and then trained using machine learning algorithms. The fixed feature design is easy to be detected by attackers, and thus deliberately avoided by attackers, reducing the generality of this method. ability

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
  • Hierarchical phishing website detection method based on deep learning
  • Hierarchical phishing website detection method based on deep learning
  • Hierarchical phishing website detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0028] The hierarchical phishing website detection method based on deep learning of the present invention, for a website to be detected, first extracts its URL and uses the low-level URL-level phishing detection module to detect the URL, and then according to the classification confidence of the URL-level phishing detection module It can adaptively choose whether to further use the high-level webpage content-level phishing detection module for detection, which can not only ensure the rapid detection of phishing websites, but also ensure high detection accuracy. Such as figure 1 As shown, this embodiment includes the following steps:

[0029] Step 1. Enter the URL of the website to be detected.

[0030] In the present invention, in the model training stage, the URL of the website to be detected is a training sample, and in the actual detection stage, it is a test sample.

[0031] Step 2. Use the URL-level phishing detection module to detect the input URL, and output the proba...

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

According to the hierarchical phishing website detection method based on deep learning, the URL and the webpage content are combined for phishing website detection, and phishing detection modules of different hierarchies can be selected and used in a self-adaptive mode for rapid and accurate phishing website detection. The method comprises the following steps: firstly, detecting an input URL; outputting the probability that the URL belongs to the phishing website; if the output probability is greater than a preset threshold value, judging that the to-be-detected website is a phishing website;otherwise, downloading a webpage corresponding to the URL to be detected; counting the number of HTML tags of the webpage, vectorizing a statistical result by utilizing an HTML tag list, extracting accurate webpage content feature representation according to a vectorized HTML tag sequence, and classifying through a full connection layer to obtain the probability that the URL belongs to a phishingwebsite.

Description

technical field [0001] The invention relates to the technical field of cyberspace security, in particular to a method for detecting hierarchical phishing websites based on deep learning. Background technique [0002] Phishing is a network attack method that uses social engineering and sophisticated information technology to steal user privacy. Attackers induce users to visit pre-designed phishing websites by sending deceptive e-mails or other communication messages, and then induce users to disclose their private data such as credit card account numbers. With the rapid development of the Internet, phishing attack techniques have become more and more complex, and the losses caused to society and economy are increasing day by day. How to quickly and effectively detect phishing websites has become a research hotspot in the field of cyberspace security. [0003] The detection method of phishing website has experienced the evolution from detection based on black and white lists,...

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 Applications(China)
IPC IPC(8): H04L29/06G06K9/62G06N3/04
CPCH04L63/1483H04L63/1416G06N3/048G06N3/044G06N3/045G06F18/24
Inventor 温武少黄永杰秦景辉
Owner SUN YAT SEN UNIV
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