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{175743,
        author = {E. Narasimhulu Naidu and Dr. K. Venkataramana},
        title = {Feature-Optimized CNN-LSTM-BiLSTM Model for SMS Threat Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {4217-4220},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175743},
        abstract = {Smishing, a combination of SMS and phishing, is a growing cybersecurity threat where malicious messages trick users into revealing sensitive information. Traditional machine learning models struggle with high false-positive rates due to similarities between legitimate and fraudulent messages. This study enhances smishing detection by integrating CNN, LSTM, and Bidirectional LSTM (BiLSTM) to improve accuracy. The CNN extracts features, while LSTM learns patterns, and BiLSTM enhances predictive performance by considering both past and future contexts. This hybrid approach achieves superior accuracy compared to existing models, reducing false positives. The extended model enhances security in mobile communications, providing a more reliable and efficient solution for smishing detection.},
        keywords = {Smishing, Cybersecurity},
        month = {April},
        }