A method, system and medium for identifying malicious URLs based on reinforcement learning

A malicious website and reinforcement learning technology, applied in the field of malicious website identification based on reinforcement learning, can solve problems such as weak robustness, improve robustness and accuracy, and reduce the risk of data leakage and property loss

Active Publication Date: 2022-03-29
CHINA ACADEMY OF INFORMATION & COMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, using the nonlinear transformation of the support vector machine and the principle of structural risk minimization to improve the generalization ability of the classifier has good classification accuracy and stability, but the classification results are not robust to the distribution of the training set and parameter configuration.

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, system and medium for identifying malicious URLs based on reinforcement learning
  • A method, system and medium for identifying malicious URLs based on reinforcement learning
  • A method, system and medium for identifying malicious URLs based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the present disclosure will be described in detail below in conjunction with the accompanying drawings and specific embodiments. Embodiments of the present disclosure will be described in further detail below in conjunction with the accompanying drawings and specific embodiments, but are not intended to limit the present disclosure. For the various steps described herein, if there is no need for a contextual relationship between each other, the order described herein as an example should not be considered as a limitation, and those skilled in the art will know that the order can be adjusted, as long as It is enough not to destroy the logic between them so that the whole process cannot be realized.

[0042] A scheme of a method for identifying a malicious website based on reinforcement learning according to an embodiment of the present disclosure will be de...

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 present disclosure relates to a method, system and medium for identifying malicious URLs based on reinforcement learning. The method includes: step S1, receiving the kth website, using the domain name blacklist to research and judge the kth website, the kth website is a website to be researched and judged, wherein k is a positive integer; step S2, in the said kth website If the domain name of the k website is not in the domain name blacklist, determine the priority of the k website, and determine the feature vector of the k website based on the priority; step S3, based on the The eigenvector of the kth website determines the test statistic Δ, and according to the test statistic Δ and the threshold θ k The k-th website is judged based on the comparison result; wherein, k is a positive integer, and N is a positive integer smaller than k.

Description

technical field [0001] The present disclosure relates to the field of malicious website identification, and more specifically, relates to a method, system and medium for identifying malicious website based on reinforcement learning. Background technique [0002] Cyber ​​attackers use malicious webpages, such as phishing webpages, Trojan horse webpages, and spam advertisement webpages, to steal sensitive user information, promote malicious software and spam advertisements, and make illegal profits. Malicious webpages seriously endanger users' information, data and property security, and the identification of malicious webpages is an urgent Internet security problem to be solved. [0003] Malicious webpage identification methods mainly include identification methods based on blacklist technology, identification methods based on heuristic rules, and identification methods based on machine learning. The identification method based on blacklist technology mainly uses URL blackli...

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): H04L9/40G06N20/00
CPCH04L63/101H04L63/1416H04L63/1483G06N20/00
Inventor 万晓玥崔现东杜伟王玉环董亚萍
Owner CHINA ACADEMY OF INFORMATION & COMM
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