Title: Phishing website detection method based on CNAIR framework

Authors: Huanhuan Wang; Debin Cheng; Hui Peng

Addresses: Fifth Electronic Research Institute of Ministry of Industry and Information Technology, No. 78, Zhucun Avenue West, Zhucun Street, Zengcheng District, Guangzhou, China ' Fifth Electronic Research Institute of Ministry of Industry and Information Technology, No. 78, Zhucun Avenue West, Zhucun Street, Zengcheng District, Guangzhou, China ' Fifth Electronic Research Institute of Ministry of Industry and Information Technology, No. 78, Zhucun Avenue West, Zhucun Street, Zengcheng District, Guangzhou, China

Abstract: At present, phishing websites are growing, and there are fewer researches on detection of phishing websites. Most of the research is based on the traditional single algorithm model, and the detection effect is not good. The feature screening and extraction methods in the past detection research are relatively fixed, and few new extraction methods have been proposed. Few researchers in detection research try to make new breakthroughs in the direction of feature extraction. This paper proposes a deep learning-based phishing website framework (CNAIR) based on deep learning algorithms for phishing website detection research. On the basis of extracting descriptive features and statistical features, the new angle features are extracted to obtain relocation features 1, relocation features 2, texture features, and word vector features. Perform all features on fusion, extract more comprehensive features, and use CNAIR framework to conduct phishing website detection research. Compared with traditional detection methods, it has a significant improvement.

Keywords: phishing website; CNAIR framework; new angle features; detection.

DOI: 10.1504/IJIPSI.2021.119167

International Journal of Information Privacy, Security and Integrity, 2021 Vol.5 No.1, pp.18 - 35

Received: 23 Mar 2021
Accepted: 26 Jun 2021

Published online: 26 Nov 2021 *

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