Year: 2025
Type: article
Abstract: In today's world, phishing creates a risk for cybersecurity attackers because they are trying to trick users by using fake websites to obtain sensitive information.To tackle this risk, we have presented an approach to identify phishing sites through the Random Forest (RF) model, a machine-learning(ML) algorithm.The goal is to increase the precision and consistency of phishing detection by implementing features and training techniques.We are utilizing a diverse collection of datasets that contain fraudulent URLs sourced from various platforms, such as Phish Tank, to develop an effective phishing detection model using the Random Forest algorithm by extracting key attributes from various URL domains and HTML formats.We have evaluated the model's effectiveness through various metrics, like accuracy, precision, recall, and F1 score, to guarantee dependable phishing identification.This will showcase the model's capability to detect phishing websites and effectively reduce the risk of users getting tricked by phishing scams.This strategy provides an implementable method for handling phishing in real-time cases.
Language: English
Topic: Spam and Phishing Detection
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4409201057