Smart Browser Extension for RealTime and Email Based Phishing Threat Detection

  • Unique Paper ID: 175471
  • PageNo: 3429-3435
  • Abstract:
  • Phishing remains a critical cybersecurity concern, where attackers exploit user trust to extract confidential data. Traditional detection mechanisms that rely exclusively on URL heuristics often fall short against modern, deceptive tactics. This research introduces a hybrid detection framework that combines URL-based feature analysis with image-based evaluation to enhance accuracy. A Random Forest model processes 30 carefully selected URL features, while a CNN evaluates webpage screenshots for visual similarities to genuine sites. The system is deployed through a browser extension that automates phishing detection in real time. To broaden its utility, the extension also offers a manual URL input feature—allowing users to verify suspicious links, including those received through emails—making it suitable for detecting email-based phishing attempts. Performance optimizations like multithreading and local caching are employed to minimize delays. Evaluation results confirm the system’s superiority over traditional approaches, offering high detection accuracy and swift response times, thereby contributing to more resilient online security solutions.

Copyright & License

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.

BibTeX

@article{175471,
        author = {Aryan Manohar Pate and Prof. Urmila G. Darekar and Nayan Prafulla Patil and Siddhesh Bhaskar Otavkar and Prathamesh Kiran Patil},
        title = {Smart Browser Extension for RealTime and Email Based Phishing Threat Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {3429-3435},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175471},
        abstract = {Phishing remains a critical cybersecurity concern, where attackers exploit user trust to extract confidential data. Traditional detection mechanisms that rely exclusively on URL heuristics often fall short against modern, deceptive tactics. This research introduces a hybrid detection framework that combines URL-based feature analysis with image-based evaluation to enhance accuracy. A Random Forest model processes 30 carefully selected URL features, while a CNN evaluates webpage screenshots for visual similarities to genuine sites. The system is deployed through a browser extension that automates phishing detection in real time. To broaden its utility, the extension also offers a manual URL input feature—allowing users to verify suspicious links, including those received through emails—making it suitable for detecting email-based phishing attempts. Performance optimizations like multithreading and local caching are employed to minimize delays. Evaluation results confirm the system’s superiority over traditional approaches, offering high detection accuracy and swift response times, thereby contributing to more resilient online security solutions.},
        keywords = {cybersecurity, real time phishing analysis, web security, anti phishing techniques},
        month = {April},
        }

Cite This Article

Pate, A. M., & Darekar, P. U. G., & Patil, N. P., & Otavkar, S. B., & Patil, P. K. (2025). Smart Browser Extension for RealTime and Email Based Phishing Threat Detection. International Journal of Innovative Research in Technology (IJIRT), 11(11), 3429–3435.

Related Articles