Malicious webpage identification method

Abstract

The invention discloses a malicious webpage identification method, which comprises the following steps: 1, acquiring the data set of a malicious webpage, and acquiring the training set and the test set of the malicious webpage through data preprocessing; 2, acquiring the character-level embedding of the training set and the test set by using a Char-CNN model; 3, constructing a BiLSTM-Attention neural network model; 4, training the BiLSTM-Attention neural network model constructed in the step 3 by utilizing the training set and the character-level embedding thereof, and static word embedding; 5, verifying the BiLSTM-Attention neural network model trained in the step 4 by utilizing the test set and the character-level embedding thereof, and static word embedding; and 6, after the verification in the step 5, performing malicious webpage identification on the webpage data accessed by a user by using the trained BiLSTM-Attention neural network model. According to the method, a bidirectionallong-short-term memory recurrent neural network based on an attention mechanism is adopted while a method of combining character-level embedding and static word embedding is also used, so that the purpose of malicious webpage identification is achieved.

Description

technical field [0001] The invention relates to the technical field of Internet security, in particular to a malicious webpage identification method. Background technique [0002] In recent years, with the continuous development of the Internet industry, the Internet has become an indispensable part of people's lives. But at the same time, malicious criminal activities using the Internet are also on the rise. Using malicious webpages to carry out phishing attacks, promote spam advertisements, and guide the download of malware are the main activities of Internet crimes. According to the <<Global Chinese Phishing Website Status Statistical Analysis Report (2016>>) and the report of the China Anti-Phishing Alliance in recent years, it can be seen that China is the country with the largest proportion of malicious web pages, and the number of malicious web pages is increasing rapidly year by year. How to quickly and effectively Identifying malicious webpages has bec...

AI Technical Summary

Problems solved by technology

However, this method is very dependent on experts in network security, and requires people who are very familiar with malicious web pages to perform manual feature extraction on malicious web page data sets

Images