Title: Research on lightweight detection model of fake domain name

Authors: Tao Ye; Jianbiao Zhang; Fengbiao Zan

Addresses: Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; College of Computer, Qinghai Nationalities University, Xining 810007, Qinghai, China ' Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China ' College of Computer, Qinghai Nationalities University, Xining 810007, China

Abstract: In recent years, phishing websites and other fake domain name attacks have become more frequent, posing a serious threat to the security of society and individuals. Fake domain name detection has become an important part of network protection. At present, fake domain name detection is mainly for public domain names, and detection methods are mainly based on edit distance. It is difficult to express the visual characteristics of domain names fully. Based on that, this paper studies the lightweight detection strategy of domain name string for the educational fake domain names and improves the detection efficiency by comprehensively considering the effect of character position, character similarity and operation type on the vision of domain name. Experimental results show that our method has a higher precision rate and recall rate on the position of the character, the character similarity, the type of operation than the traditional edit distance algorithms.

Keywords: educational domain name; fake domain name; edit distance; visual similarity.

DOI: 10.1504/IJWMC.2021.115643

International Journal of Wireless and Mobile Computing, 2021 Vol.20 No.3, pp.264 - 271

Received: 06 Aug 2020
Accepted: 18 Sep 2020
Published online: 15 Jun 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article