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{200544,
        author = {Parth Goel and Reshita Chaudhary and Snigdha Som and Rishika Yadav},
        title = {Scam Shield- A Hybrid ML–NLP–XAI Framework for Real-Time Phishing Detection and Explainable Cybersecurity Awareness},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {1474-1482},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200544},
        abstract = {Phishing and online scams are nowadays becoming the face of a cybersecurity threat which is breaking people’s trust as well as they are now tending to steal the personal and sensitive data of any particular person or a client of any company. Despite of being progressing in the area of Machine Learning, deep learning and Natural Language Processing, still in today’s world current solutions do not have the ability to adapt, to explain and to user centered design.
This paper offers Scam Shield- which is a mixture of Machine Learning (ML), Natural Language Processing (NLP), Explainable Artificial Intelligence (XAI). It works on the browser and also as a web platform which is made up by integrating the mentioned three technologies. It mostly works for real time scan and for any type of phishing detection. This whole made up system analyses all the given Uniform Resource Locator, any content on the web page, any changes in behavior, any website which is classified to be put into a category safe, suspicious and malicious. By using Explainable Artificial Intelligence, Scam Shield provides early alerts which will work as an alarm and then explain why this particular website or Uniform Resource Locator is not safe to visit.
Results showed improve in accuracy, in a smaller number of false positives and it also has increased the whole user engagement if we compare it to before from now. Therefore, this model’s feedback reloads continuously and update its dataset and ensure for the adaptation against emerging scams.},
        keywords = {Cybersecurity, Phishing detection, Machine Learning, Natural Language Processing, Explainable Artificial Intelligence, Browser Extension, Adapting Conditions.},
        month = {May},
        }