Harmful website classification method

Method for classifying harmful websites through domain access screening and HTML analysis

This technology relates to a method of identifying accessible websites by modifying numbers in domain addresses and classifying them as harmful or safe by analyzing their HTML source code.

Existing harmful site blocking methods struggle to keep up with domains that are frequently closed or changed, and they face difficulties in automatically classifying a vast number of websites.

To address this, this technology combines domain number modification-based access screening with HTML source code analysis to automatically collect and classify accessible websites.

This invention is the result of the 'AI Information Collection for Monitoring Illegal Content Distribution Sites' project, supported by the Ministry of SMEs and Startups.

‍

‍

Key Features:

• A step of extracting numbers from a domain address, modifying the positions of the numbers, and repeatedly attempting access to identify accessible websites
• A step of extracting and preprocessing the HTML source code of accessible websites
• A step of analyzing the preprocessed HTML source code to determine whether the website is harmful
• A step of classifying the website as a harmful site based on the determination results