Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

An Algorithm-Generated Domain Name Detection Method Based on Natural Language-like Features

A technology of natural language and domain name detection, applied in transmission systems, electrical components, etc., can solve problems such as poor versatility, and achieve the effect of improving detection accuracy, strong versatility, and reducing detection false alarm rate

Active Publication Date: 2019-07-23
成都蜀道易信科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide an algorithm-generated domain name detection method based on natural language-like features, which solves the problem of poor versatility for specific attacks or specific environments, and can detect endlessly emerging new algorithm-generated domain names. Carry out hierarchical feature extraction for each domain name to improve the accuracy of detection

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
  • An Algorithm-Generated Domain Name Detection Method Based on Natural Language-like Features
  • An Algorithm-Generated Domain Name Detection Method Based on Natural Language-like Features
  • An Algorithm-Generated Domain Name Detection Method Based on Natural Language-like Features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. The method of the present invention comprises the following steps: 1) selecting a domain name corpus, and using a feature extraction module to perform feature extraction on the domain name corpus; 2) performing parameter learning on the domain name corpus, obtaining system parameters of various features to obtain a detection model based on the corpus; 3) Obtain the request domain name information of the DNS server through the data packet sniffing module; 4) use the feature extraction module to perform feature extraction according to the request domain name information, and detect the domain name according to the detection model.

[0035] The domain name corpus selects Alexa TOP one million domain names and PadCrypt, QADARS, LOCKY domain name generation algorithms to generate domain names. Alexa is currently the website with the largest ...

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 domain name detection method based on an algorithm-generated natural language feature, comprising the following steps: Step 1: Select a domain name corpus, and use a feature extraction module to perform feature extraction on the domain name corpus; Step 2: Carry out parameter learning on the domain name corpus , to obtain the system parameters of each feature, and obtain a detection model based on the corpus; Step 3: Obtain the requested domain name information of the DNS server through the packet sniffing module; Step 4: Use the feature extraction module to perform feature extraction according to the requested domain name information; Step 5 : Detect the domain name according to the detection model in the real environment. The invention can detect the domain names generated by novel algorithms emerging one after another, classify the domain names and extract the features of each domain name respectively, thereby improving the accuracy of detection.

Description

technical field [0001] The invention relates to the field of algorithm-generated domain name detection, in particular to an algorithm-generated domain name detection method based on natural language-like features. Background technique [0002] The domain name system is a bridge connecting users and the Internet in the Internet, but due to the vulnerability of its own protocol design, a large number of malicious behaviors are controlled and attacked through the domain name system, such as botnets, Trojan horse viruses and advanced persistent threats (Advanced Persistent Threat, APT ) attack etc. At the same time, domain name generation technologies such as DNS positioning technology and fast domain name conversion technology are widely used in network attacks, so it is particularly important to detect generated domain names. At present, the detection of algorithm-generated domain names can be mainly divided into the following two categories: 1) Real-time or quasi-real-time D...

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): H04L29/12H04L29/06
CPCH04L63/1441H04L63/1483H04L2463/144H04L61/4511
Inventor 陈兴蜀朱毅江天宇曾雪梅陈敬涵
Owner 成都蜀道易信科技有限公司
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
Eureka Blog
Learn More
PatSnap group products