Identification of Phishing Attacks using Machine Learning Algorithm

¹ Department of Electronics and Communication Engineering, Sona College of Technology, Salem, India
² Spring Five, Bangalore, India
³ Department of Electronics and Communication Engineering, K.Ramakrishnan College of Technology, Trichy - 621112, Tamil Nadu, India

^* Corresponding author: pmdineshece@live.com

Abstract

Phishing is a particular type of cybercrime that allows criminals to trick people and steal crucial data. The phishing assault has developed into a more complex attack vector since the first instance was published in 1990. Phishing is currently one of the most prevalent types of online fraud behavior. Phishing is done using a number of methods, such as through emails, phone calls, instant chats, adverts, pop-up windows on websites, and DNS poisoning. Phishing attacks can cause their victims to suffer significant losses, including the loss of confidential information, identity theft, businesses, and state secrets. By examining current phishing practises and assessing the state of phishing, this article seeks to assess these attacks. This article offers a fresh, in-depth model of phishing that takes into account attack stages, different types of attackers, threats, targets, attack media, and attacking strategies. Here, we categorise websites as real or phishing websites using machine learning techniques including Random Forest, XGBoost, and Logistic Regression. Additionally, the proposed anatomy will aid readers in comprehending the lifespan of a phishing attack, raising awareness of these attacks and the strategies employed as well as aiding in the creation of a comprehensive anti-phishing system.