Machine Learning-Based Fraudulent and Harmful Link Detection System - Volume 14 - April 2025

Aug 4, 2026

Phishing attacks leverage malicious websites that mimic legitimate pages to obtain sensitive information such as passwords, account details, and card data. Detecting phishing remains an unstable and complex problem because attackers continuously adopt new and hybrid strategies to bypass existing defenses. Prior approaches using fuzzy logic, neural networks, and data mining can support effective identification. The study applies the Random Forest (RF) machine learning algorithm for phishing website detection and compares classifier performance using accuracy metrics.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

ABSTRACT

KEYWORDS

Figure 1: SYSTEM ARICHITECTURE

I. INTRODUCTION

Phishing overview and evolving attack techniques

II. LITERATURE REVIEW

ML-based phishing detection and Random Forest background

III. METHODOLOGY

Dataset preparation, feature selection, training and evaluation

IV. IMPLEMENTATION

Data set challenges

International Journal of Innovative Research in Science Engineering and Technology (IJIRSET) (A Monthly, Peer Reviewed, Refereed, Scholarly Indexed, Open Access Journal) Impact Factor: 8.699 Volume 14, Issue 4 , April 2025 |
|[www.ijirset.com](www.ijirset.com |A Monthly)[ |A Monthly](www.ijirset.com |A Monthly), Peer Reviewed & Refereed Journal| e-ISSN: 2319-8753| p-ISSN: 2347-6710|
Volume 14, Issue 4, April 2025
|DOI: 10.15680/IJIRSET.2025.1404503|
Machine Learning-Based Fraudulent and Harmful Link Detection System

| | --- | |
Associate Professor, Department of CSE, Bharath Institute of Higher Education and Research, Selaiyur, Chennai, India B. Tech Students, Department ofCSE, Bharath Institute of Higher Education and Research, Selaiyur, Chennai, India | | ABSTRACT: Phishing sites which expects to take the victims confidential data by diverting them to surf a fake website page that resembles a honest to goodness one is another type of criminal acts through the internet and its one of the especially concerns toward numerous areas including e-managing an account and retailing. Phishing site detection is truly an unpredictable and element issue including numerous components and criteria that are not stable. On account of the last and in addition ambiguities in arranging sites because of the intelligent procedures programmers are utilizing, some keen proactive strategies can be helpful and powerful tools can be utilized, for example, fuzzy, neural system and data mining methods can be a successful mechanism in distinguishing phishing sites. We applied Random Forest (RF), one of the different types of machine learning based algorithms used for detection of Phishing websites. Finally we measured and compared the performance of the classifier in terms of accuracy.

KEYWORDS: Phishing Website Detection, Cybersecurity, Random Forest (RF), Machine Learning.

Figure 1: SYSTEM ARICHITECTURE

I. INTRODUCTION | |
Phishing is a type of extensive fraud that happens when a malicious website act like a real one keeping in mind that the end goal to obtain touchy data, for example, passwords, account points of interest, or MasterCard numbers.In spite of the fact that there are a few contrary to phishing programming and methods for distinguishing potential phishing endeavours in messages and identifying phishing substance on sites, phishes think of new and half breed strategies togo around the accessible programming and systems.Phishing is a trickery system that uses a blend of social designing | | IJIRSET©2025 | An ISO 9001:2008 Certified Journal | 9506 | S. Sarjun Beevi, Venanka Sai Nithin, Kavati Venkatesh, Chintala Sai Rohit, Vardineni Shiva Teja |
|[www.ijirset.com](www.ijirset.com |A Monthly)[ |A Monthly](www.ijirset.com |A Monthly), Peer Reviewed & Refereed Journal| e-ISSN: 2319-8753| p-ISSN: 2347-6710|
Volume 14, Issue 4, April 2025
|DOI: 10.15680/IJIRSET.2025.1404503| | | --- | |
what's more, innovation to assemble delicate and individual data, for example, passwords and charge card subtle elements by taking on the appearance of a dependable individual or business in an electronic correspondence. Phishing makes utilization of spoof messages that are made to look valid and implied to be originating from honest to goodness sources like money related foundations, ecommerce destinations and so forth, to draw clients to visit fake sites through joins gave in the phishing email. The misleading sites are intended to emulate the look of a genuine organization site page. | |
II. LITERATURE REVIEW | |
Phishing attacks have become one of the most prevalent threats in the domain of cybersecurity. These attacks typically involve tricking users into revealing sensitive information such as usernames, passwords, and credit card details through websites that closely mimic legitimate ones. As phishing techniques continue to evolve in sophistication, traditional blackl

FAQs

What is the primary focus of this system?

The system focuses on detecting phishing websites and fraudulent or harmful links using machine learning techniques, specifically the Random Forest model.

Why is phishing detection considered difficult?

Phishing sites change rapidly and use new hybrid social-engineering strategies, making rule-based or blacklisting approaches insufficient for newly created and evolving threats.

How does the Random Forest approach work in the study?

The method extracts features from URL, domain, and page content, trains a Random Forest classifier using an ensemble of decision trees, and predicts classes through majority voting.

Aug 4, 2026

Upload by River Wang