Application of Machine Learning for Real-Time Phishing Attack Detection

Over the years, the Internet has been exploited to carry out a range of cyber attacks, with phishing being the most prominent one. Increasingly sophisticated techniques of phishing have threatened the security of many Internet-based systems. To be able to detect suspicious websites is a potential f...

Full description

Saved in:
Bibliographic Details
Main Authors: Akshay Shankar Agrawal, Sanketi Raut, Andrina Dsouza, Jimit Mehta, Prajwal Naik
Format: Article
Language:English
Published: Institute of Technology and Education Galileo da Amazônia 2025-06-01
Series:ITEGAM-JETIA
Online Access:http://itegam-jetia.org/journal/index.php/jetia/article/view/1652
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849417692144992256
author Akshay Shankar Agrawal
Sanketi Raut
Andrina Dsouza
Jimit Mehta
Prajwal Naik
author_facet Akshay Shankar Agrawal
Sanketi Raut
Andrina Dsouza
Jimit Mehta
Prajwal Naik
author_sort Akshay Shankar Agrawal
collection DOAJ
description Over the years, the Internet has been exploited to carry out a range of cyber attacks, with phishing being the most prominent one. Increasingly sophisticated techniques of phishing have threatened the security of many Internet-based systems. To be able to detect suspicious websites is a potential first step in reducing the amount of phishing attacks occurring daily. This paper outlines the development and implementation of a platform to detect phishing websites. It highlights the pressing need for early detection of possible phishing attacks to prevent data theft, frauds, etc. The system uses machine learning algorithms to distinguish legitimate websites from phishing websites and generate a prediction to be used for the platform. A user interface is implemented to have two parts. The first part includes a text field for entering a URL, which the ML model processes to give a prediction that gets displayed to the user. Another module gathers URLs as they arrive from an API and scans them for potentially suspicious websites. The final ML model, a Random Forest classifier with 27 estimators, had an accuracy of 96.12% and F1 score of 95.94%. Future enhancements and research directions are also discussed for further development of the system.
format Article
id doaj-art-8b7fd5703af842b8aaea82f2dd661934
institution Kabale University
issn 2447-0228
language English
publishDate 2025-06-01
publisher Institute of Technology and Education Galileo da Amazônia
record_format Article
series ITEGAM-JETIA
spelling doaj-art-8b7fd5703af842b8aaea82f2dd6619342025-08-20T03:32:41ZengInstitute of Technology and Education Galileo da AmazôniaITEGAM-JETIA2447-02282025-06-01115310.5935/jetia.v11i53.1652Application of Machine Learning for Real-Time Phishing Attack DetectionAkshay Shankar Agrawal0Sanketi Raut1Andrina Dsouza2Jimit Mehta3Prajwal Naik4UNIVERSITY OF MUMBAIUniversity of Mumbai, Mumbai. India.Department of Information Technology, Universal College of Engineering, University of Mumbai, Vasai, India.Department of Information Technology, Universal College of Engineering, University of Mumbai, Vasai, India.Department of Information Technology, Universal College of Engineering, University of Mumbai, Vasai, India. Over the years, the Internet has been exploited to carry out a range of cyber attacks, with phishing being the most prominent one. Increasingly sophisticated techniques of phishing have threatened the security of many Internet-based systems. To be able to detect suspicious websites is a potential first step in reducing the amount of phishing attacks occurring daily. This paper outlines the development and implementation of a platform to detect phishing websites. It highlights the pressing need for early detection of possible phishing attacks to prevent data theft, frauds, etc. The system uses machine learning algorithms to distinguish legitimate websites from phishing websites and generate a prediction to be used for the platform. A user interface is implemented to have two parts. The first part includes a text field for entering a URL, which the ML model processes to give a prediction that gets displayed to the user. Another module gathers URLs as they arrive from an API and scans them for potentially suspicious websites. The final ML model, a Random Forest classifier with 27 estimators, had an accuracy of 96.12% and F1 score of 95.94%. Future enhancements and research directions are also discussed for further development of the system. http://itegam-jetia.org/journal/index.php/jetia/article/view/1652
spellingShingle Akshay Shankar Agrawal
Sanketi Raut
Andrina Dsouza
Jimit Mehta
Prajwal Naik
Application of Machine Learning for Real-Time Phishing Attack Detection
ITEGAM-JETIA
title Application of Machine Learning for Real-Time Phishing Attack Detection
title_full Application of Machine Learning for Real-Time Phishing Attack Detection
title_fullStr Application of Machine Learning for Real-Time Phishing Attack Detection
title_full_unstemmed Application of Machine Learning for Real-Time Phishing Attack Detection
title_short Application of Machine Learning for Real-Time Phishing Attack Detection
title_sort application of machine learning for real time phishing attack detection
url http://itegam-jetia.org/journal/index.php/jetia/article/view/1652
work_keys_str_mv AT akshayshankaragrawal applicationofmachinelearningforrealtimephishingattackdetection
AT sanketiraut applicationofmachinelearningforrealtimephishingattackdetection
AT andrinadsouza applicationofmachinelearningforrealtimephishingattackdetection
AT jimitmehta applicationofmachinelearningforrealtimephishingattackdetection
AT prajwalnaik applicationofmachinelearningforrealtimephishingattackdetection