Malicious website detection method and device, electronic equipment and computer storage medium

Abstract

The invention relates to the technical field of network information security, and provides a malicious website detection method and device, electronic equipment and a computer storage medium, and the method comprises the steps: determining suspected malicious websites in to-be-detected websites based on the obtained domain name and / or webpage content of each to-be-detected website; according to the fact that the webpage content of each suspected malicious website comprises text content, determining text features of each suspected malicious website; based on a pre-trained clustering model, according to the text features of each suspected malicious website, clustering each suspected malicious website to obtain a clustering category corresponding to each suspected malicious website; based on a preset sensitive word bank, determining sensitive types of the clustering categories to obtain sensitive types of all the suspected malicious websites corresponding to the clustering categories; and determining the risk level of the suspected malicious website according to the sensitive type of the suspected malicious website, and determining whether the suspected malicious website is a malicious website based on the risk level. According to the method and device, the malicious website identification and classification accuracy can be improved.

Description

technical field [0001] The present disclosure relates to the technical field of network information security, and in particular to a malicious website detection method, device, electronic equipment and computer storage medium. Background technique [0002] Home broadband has a large number of customers, and hundreds of millions of network visits per day cover various types of websites such as e-commerce, live video, and chess and card games. However, the Internet is full of all kinds of malicious content. Originally a normal website, after the user clicks a normal link, the webpage sometimes jumps directly to a malicious website. This will not only bring fraud risks to users and cause economic losses, but also cause users to refuse to use home broadband again due to impaired product experience, resulting in huge reputation loss and user loss for home broadband. In addition, the professionalization and automation of malicious websites continue to increase, making technical ...

AI Technical Summary

Problems solved by technology

The first type of method mainly determines whether a website is a malicious website by judging whether the text data of the website contains preset keywords. However, this method relies too much on keywords, and inaccurate keywords or untimely updates will lead to malicious websites. The accuracy of recognition drops

The second type of method is mainly to identify the corresponding website collection through different identification models. However, this method cannot effectively distinguish malicious websites from non-malicious websites.

The third type of method mainly determines whether the website is an illegal website by judging whether the URL (Uniform ResourceLocator, uniform resource locator) of the website is the URL of the illegal website included in the blacklist. However, this method relies too much on the blacklist, and Unable to determine illegal type of illegal website

Images