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{195355,
        author = {C.Saibaba and V.Sandya and N.Harshavardhan and P.Ritish},
        title = {SMS -URL Sentinel: Dual Detection System Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {130-133},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195355},
        abstract = {The recent attempts of the mobile communication and online services have exposed online and mobile users to unsolicited SMS spam, malicious URLs, which are both a big threat in terms of privacy, security, and integrity of the device. This project introduces a three-dimensional, dual-module system that will resolve these issues with the use of advanced techniques in machine learning. The former module is dedicated to SMS spammy texting of SMS in English, Hindi and mixed message (English and Hindi) with mBERT, which is transfers-based technology able to consider semantic subtleties and context in short text messaging. The level of deep contextualization allows it to classify with a lot of force even with different linguistic patterns. In addition to this the second module uses a Random Forest based method to detect malicious URLs using ensemble learning of potential suspicious patterns of web URL format and related metadata that can be very dependable. In combination with integrating both detection channels into one the project is able to provide a layered protection option that is capable of both proactively filtering the harmful SMS contents and also averting the users to dangerous web links. This hybrid method has the benefit of supporting better security globally as well as mitigating false positives with the use of cross-module validation. The combined framework shows a good performance in the evaluation measures and hence proposes that it can be deployed to the real-life mobile and web environments as a holistic threat-mitigation system.},
        keywords = {SMS Spam Detection, Malicious URL Detection, mBERT, Random Forest, Integrated Detection System.},
        month = {April},
        }