Abstract :

In The Rapidly Evolving Digital World, Cybersecurity Threats Have Become A Major Concern, With Phishing Attacks Being One Of The Most Common And Harmful Forms Of Cybercrime. Phishing Involves Creating Fraudulent Websites Or Malicious URLs That Imitate Legitimate Platforms To Deceive Users Into Revealing Sensitive Information Such As Login Credentials, Banking Details, And Personal Data. Traditional Phishing Detection Techniques, Including Blacklist-based And Heuristic Methods, Are Often Ineffective Against Newly Emerging And Sophisticated Attacks. This Project Presents An Intelligent Phishing Detection System Based On Machine Learning Techniques, Focusing On URL-based Analysis. A Comprehensive Dataset Containing More Than 11,000 Phishing And Legitimate URLs Is Used For Training And Testing The Models. Various Machine Learning Algorithms Such As Decision Tree, Random Forest, Naive Bayes, Support Vector Machine, K-Nearest Neighbors, And Gradient Boosting Are Implemented To Classify URLs. To Enhance Performance, A Hybrid Model Named LSD (Logistic Regression + Support Vector Machine + Decision Tree) Is Proposed Using Ensemble Voting Techniques. Additionally, Feature Selection Methods, Cross-validation, And Grid Search Hyperparameter Optimization Are Applied To Improve Accuracy And Efficiency. The System Is Evaluated Using Metrics Such As Accuracy, Precision, Recall, F1-score, And Specificity. Experimental Results Demonstrate That The Proposed Hybrid Model Outperforms Individual Machine Learning Models, Providing Higher Accuracy And Reduced False Positives. The Developed System Offers A Reliable And Scalable Solution For Real-time Phishing Detection, Thereby Enhancing User Security And Protecting Sensitive Information In Online Environments.

Published:

22-5-2026

Issue:

Vol. 26 No. 5 (2026)

Page Nos:

1464-1470

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite