
Целью работы ÑвлÑетÑÑ Ð¾Ð¿Ñ€ÐµÐ´ÐµÐ»ÐµÐ½Ð¸Ðµ наиболее Ñффективного метода машинного Ð¾Ð±ÑƒÑ‡ÐµÐ½Ð¸Ñ Ð´Ð»Ñ Ð¾Ð±Ð½Ð°Ñ€ÑƒÐ¶ÐµÐ½Ð¸Ñ Ñ„Ð¸ÑˆÐ¸Ð½Ð³Ð¾Ð²Ñ‹Ñ… веб-Ñайтов. Предметом иÑÑÐ»ÐµÐ´Ð¾Ð²Ð°Ð½Ð¸Ñ ÑвлÑÑŽÑ‚ÑÑ Ñовременные методы Ð¾Ð±Ð½Ð°Ñ€ÑƒÐ¶ÐµÐ½Ð¸Ñ Ñ„Ð¸ÑˆÐ¸Ð½Ð³Ð¾Ð²Ñ‹Ñ… веб-Ñайтов. Задачи, решаемые в ходе иÑÑледованиÑ: 1. Сформировать набор данных и разработать ÑредÑтво раÑÑˆÐ¸Ñ€ÐµÐ½Ð¸Ñ Ð½Ð°Ð±Ð¾Ñ€Ð° данных. 2. ПровеÑти анализ применÑемых методов Ð´Ð»Ñ Ð¾Ð±Ð½Ð°Ñ€ÑƒÐ¶ÐµÐ½Ð¸Ñ Ñ„Ð¸ÑˆÐ¸Ð½Ð³Ð¾Ð²Ñ‹Ñ… веб-Ñайтов, выбрать методы Ð´Ð»Ñ Ð´Ð°Ð»ÑŒÐ½ÐµÐ¹ÑˆÐµÐ³Ð¾ иÑÑледованиÑ. 3. Разработать программный прототип Ð´Ð»Ñ Ð¾Ð±Ð½Ð°Ñ€ÑƒÐ¶ÐµÐ½Ð¸Ñ Ñ„Ð¸ÑˆÐ¸Ð½Ð³Ð¾Ð²Ñ‹Ñ… веб-Ñайтов Ñ Ð¿Ð¾Ð¼Ð¾Ñ‰ÑŒÑŽ выбранных методов. 4. ПровеÑти Ñравнительный анализ методов машинного Ð¾Ð±ÑƒÑ‡ÐµÐ½Ð¸Ñ Ð² обнаружении фишинговых веб-Ñайтов. Ð’ ходе работы были иÑÑледованы применÑемые методы Ð´Ð»Ñ Ð¾Ð±Ð½Ð°Ñ€ÑƒÐ¶ÐµÐ½Ð¸Ñ Ñ„Ð¸ÑˆÐ¸Ð½Ð³Ð¾Ð²Ñ‹Ñ… веб-Ñайтов. Была решена задача Ñ„Ð¾Ñ€Ð¼Ð¸Ñ€Ð¾Ð²Ð°Ð½Ð¸Ñ Ð½Ð°Ð±Ð¾Ñ€Ð° данных. Ð’ результате работы были разработаны программный прототип Ð´Ð»Ñ Ð¾Ð±Ð½Ð°Ñ€ÑƒÐ¶ÐµÐ½Ð¸Ñ Ñ„Ð¸ÑˆÐ¸Ð½Ð³Ð¾Ð²Ñ‹Ñ… веб-Ñайтов и ÑредÑтво раÑÑˆÐ¸Ñ€ÐµÐ½Ð¸Ñ Ð½Ð°Ð±Ð¾Ñ€Ð° данных, был проведен Ñравнительный анализ методов машинного Ð¾Ð±ÑƒÑ‡ÐµÐ½Ð¸Ñ Ð´Ð»Ñ Ð¾Ð±Ð½Ð°Ñ€ÑƒÐ¶ÐµÐ½Ð¸Ñ Ñ„Ð¸ÑˆÐ¸Ð½Ð³Ð¾Ð²Ñ‹Ñ… веб-Ñайтов.
The aim of the work is to determine the most effective machine learning method for detecting phishing websites. The subject of the study is modern methods for detecting phishing websites. Tasks to be solved in the course of the study: 1. Form a data set and develop a tool for extending the data set. 2. Conduct an analysis of the methods used to detect phishing websites, select methods for further research. 3. Develop a software prototype to detect phishing websites using selected methods. 4. Conduct a comparative analysis of machine learning methods in detecting phishing websites. In the course of the work, the methods used to detect phishing websites were investigated. The problem of forming a data set was solved. As a result of the work, a software prototype for detecting phishing websites and a tool for expanding the data set were developed, and a comparative analysis of machine learning methods for detecting phishing websites was carried out.
веб-ÑайÑÑ, клаÑÑиÑикаÑиÑ, machine learning, websites, classification, маÑинное обÑÑение, ÑиÑинг, phishing
веб-ÑайÑÑ, клаÑÑиÑикаÑиÑ, machine learning, websites, classification, маÑинное обÑÑение, ÑиÑинг, phishing
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
