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{193484,
        author = {Merin c shajan and Umaira.K.U and Amarnath M},
        title = {Phishing URL Detection Intelligent Phishing Detection System Using URL and Email Pattern Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {523-528},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193484},
        abstract = {The rapid growth of digital communication platforms, online banking, cloud services, and e-commerce systems has significantly increased exposure to phishing attacks. Phishing remains one of the most prevalent cyber threats, exploiting deceptive URLs and fraudulent emails to steal sensitive information such as login credentials, financial data, and personal details. Traditional blacklist-based detection mechanisms are limited in their ability to identify newly generated or zero-day phishing URLs, as they rely on previously reported malicious links. To address these limitations, this paper proposes an Intelligent Phishing Detection System that integrates URL structure analysis and email pattern recognition using machine learning techniques. The proposed system employs a multi-layered architecture that collects URLs and email data from various input sources, performs preprocessing and feature extraction, and applies hybrid machine learning models for classification. URL-based features include lexical characteristics, domain age, WHOIS and DNS attributes, HTTPS certificate validation, and URL shortening detection. Email-based features analyze header anomalies, sender domain authentication (SPF, DKIM, DMARC concepts), urgency keywords, and embedded hyperlink mismatches. Multiple algorithms such as Logistic Regression, Random Forest, Support Vector Machine, Gradient Boosting, and deep learning models (LSTM/CNN) are utilized to enhance detection accuracy and zero-day threat identification. Experimental evaluation demonstrates high accuracy, strong recall, and improved detection performance compared to traditional blacklist systems. The proposed approach provides proactive, adaptive, and scalable phishing protection, significantly enhancing cybersecurity resilience across enterprise and financial environments.},
        keywords = {Phishing URL Detection, Machine Learning, Email Pattern Analysis, Cybersecurity.},
        month = {March},
        }