Machine Learning Methods for Phishing Attacks: Survey

Mirat Medelbekov, Marat Nurtas

2023

DOI 10.1109/sist58284.2023.10223537

Data confidence 85 high

How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The basis of cybersecurity is an understanding of the mechanisms of social engineering. This increases the effectiveness in combating this type of manipulation. One of them is phishing. Phishing attacks actively exploit the human factor to collect credentials or distribute malware. Machine learning has been successfully used to detect and prevent phishing. The purpose of this study is to review machine learning methods and the results of previous studies to prevent phishing attacks. Further studies will be planned based on this work.