Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{203252,
        author = {N. Nagamani and Dr. R.Prasad Rao and B. Siva Sai and B. Vedavyas Naidu and K. Gowthami and K. Pavani},
        title = {INTELLIGENT PHISHING URL DETECTION SYSTEM USING MACHINE LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {10476-10480},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203252},
        abstract = {The Intelligent Phishing URL Detection System Using Machine Learning is developed to identify malicious and fraudulent URLs through the analysis of structural and lexical characteristics of web links. Phishing attacks represent one of the most widespread cyber threats, where attackers deceive users using fake URLs that imitate legitimate websites. To address this issue, the proposed system employs machine learning algorithms to classify URLs as either legitimate or malicious based on extracted URL features.
The application is implemented using Python and Streamlit, providing an interactive and user-friendly interface. Multiple machine learning algorithms such as Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) are integrated into the system for classification. Automated feature extraction techniques are used to analyze parameters including URL length, special character count, IP address presence, suspicious keywords, HTTPS usage, and digit-to-letter ratio.
A synthetic dataset consisting of legitimate domains, phishing-oriented keyword domains, and suspicious URLs is generated for training and testing purposes. Each model is evaluated using performance metrics, and the final classification is obtained through a majority voting mechanism among all classifiers. The system also includes a secure login interface, real-time URL validation, and graphical visualization of model confidence levels.
By combining machine learning with cyber security principles, the proposed system offers an effective solution for phishing detection. The project demonstrates how intelligent cyber defense mechanisms can improve online security awareness and protect users from malicious websites.},
        keywords = {Phishing Detection, Machine Learning, URL Analysis, Cyber security, Ensemble Learning, Streamlit, URL Classification.},
        month = {May},
        }