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{175397,
        author = {Abhinav Dyan Samantara and Dr. Vanitha Kakollu},
        title = {Phishing Link Detection Using Machine Learning, Flask and Web Technologies},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {11},
        number = {11},
        pages = {4315-4322},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175397},
        abstract = {Phishing attacks are a serious cybersecurity risk in which individuals and businesses are targeted with the intention of stealing private data, involving financial in-formation, usernames, and passwords. Phishing attacks are carried out by means of misleading links in emails, messages, or fake websites that imitate authentic websites. Rule-based detection techniques are no longer adequate because of the evolving nature of phishing attacks, par-ticularly when obfuscation techniques like domain spoof-ing and URL shortening are used. This situation requires the employment of sophisticated and adaptive detection systems.
To identify if a URL is authentic or phishing, the project plans to create a Phishing Link Detection System using machine learning (ML). System identifies notable fea-tures—lexical patterns, host-based features, and struc-tural features—to train an ML model to detect phishing correctly. In contrast to static rule-based systems, the ML-based system learns new phishing patterns with time and hence increases detection accuracy.
Real-time URL analysis is supported by a Flask-based user interface, which lets users enter URLs and get pre-dictions about the chance of phishing. System also pro-vides explanations for predictions and stores detection re-sults in a backend database for monitoring and analysis. With the inclusion of ML-based analysis, real-time detec-tion, and user awareness, this project offers an effective solution to counter phishing attacks and enhance cyber-security awareness.},
        keywords = {phishing, machine learning, cybersecurity, URL classification, browser extension, feature engineering},
        month = {February},
        }