A phishing website URL detection method based on depth learning

Abstract

The invention discloses a phishing website URL detection method based on depth learning, which can detect the phishing website on the Internet in real time only according to the website URL. At first,the URL string sequence is encoded into one-Hot two-dimensional sparse matrix, then transformed into dense character embedding matrix and input to a convolution neural network, local depth features are extracted, and then the input and the output of convolution neural network are input to long-term and short-term memory network, the correlation of URL sequences is captured, and finally a softmaxmodel is accessed to classify URLs. The invention can avoid redundant feature engineering, extract local depth correlation feature through convolution neural network, learn long-range dependency in URL through long-term and short-term memory network, and quickly and accurately detect phishing website URL.

Description

Technical field [0001] The invention relates to a method for detecting URL of a phishing website based on deep learning. The method extracts relevant characteristics of URL string sequence, uses a deep learning method to improve classification accuracy, can detect phishing websites on the Internet in real time, and belongs to the technical field of cyberspace security. Background technique [0002] In recent years, with the rapid development of the Internet, the security deficiencies of the Internet architecture have become increasingly apparent, and various security issues such as phishing, cybercrime, and privacy leakage have become more prominent. Without cyber security, there can be no national security. Cyberspace security has become a problem that all countries in the world must face and solve together. Among various network security issues, phishing is a criminal act of stealing personal information of website users through social engineering or other complex technical mea...

AI Technical Summary

Problems solved by technology

This method mainly includes processes such as URL character embedding representation, CNN-LSTM classification model, and model training. It can effectively capture the association and semantic information before and after characters in the URL character sequence, and effectively solve the problem that traditional phishing website detection methods based on URL features cannot fully reflect phishing. The problem of website URL characteristics, and apply convolutional neural network and long-term short-term memory network model to phishing website detection, improve detection accuracy and reduce detection false negative rate

Images