COMPARATIVE STUDY OF ML ALGORITHMS FOR PHISHING DETECTION

Authors

  • V. Ramya, N.Haripriya, G.Dinesh , P.Chandana ,A.Bhaskaranjani, K.Sudheer Author

DOI:

https://doi.org/10.62643/

Keywords:

Phishing detection, phishing websites, machine learning, URL-based features, cybersecurity, random forest, support vector machine, decision tree, feature extraction, classification, anomaly detection, web security, social engineering.

Abstract

Phishing attacks continue to pose a significant cybersecurity threat by exploiting user trust to obtain sensitive information such as login credentials and financial data. Existing detection techniques, including blacklist-based and similarity-based approaches, often fail to identify zero-day attacks and suffer from delayed response or high computational overhead. To address these limitations, this study proposes an efficient machine learning-driven framework for phishing website detection using URL-based feature analysis. The proposed system extracts discriminative lexical and structural characteristics from URLs and employs multiple supervised learning algorithms, namely Decision Tree, Support Vector Machine, and Random Forest, to classify websites as legitimate or malicious. A comparative evaluation is conducted using standard performance metrics such as accuracy, precision, recall, F1-score, and error rates. Experimental results demonstrate that ensemble-based learning, particularly the Random Forest model, achieves superior performance with an accuracy of 96.8% and reduced false positive and false negative rates. Unlike traditional approaches, the proposed mechanism enables automated and real-time detection without reliance on external blacklists. This makes it more robust against evolving phishing strategies. The findings highlight the effectiveness of machine learning models in enhancing phishing detection systems and provide a scalable solution for securing web-based platforms and user interactions.

Downloads

Published

04-04-2026

How to Cite

COMPARATIVE STUDY OF ML ALGORITHMS FOR PHISHING DETECTION . (2026). International Journal of Engineering Research and Science & Technology, 22(2), 861-867. https://doi.org/10.62643/