A Comparative Analysis of Deep Learning Models for Smishing Detection in SMS Message
Aqsa Shaikh1, Mariya Shaikh2, Srivaramangai R3
1Aqsa Shaikh, Student, Department of Information Technology, University of Mumbai, Mumbai (Maharashtra), India.
2Mariya Shaikh, Student, Department of Information Technology, University of Mumbai, Mumbai (Maharashtra), India.
3Srivaramangai R., Head, Department of Information Technology, University of Mumbai, Mumbai (Maharashtra), India.
Manuscript received on 01 March 2026 | Revised Manuscript received on 09 March 2026 | Manuscript Accepted on 15 March 2026 | Manuscript published on 30 March 2026 | PP: 14-21 | Volume-14 Issue-6, March 2026 | Retrieval Number: 100.1/ijrte.A834515010526 | DOI: 10.35940/ijrte.A8345.14060326
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Smishing (SMS phishing) is a cyber threat that is growing rapidly, and it’s a tactic in which attackers use SMS messages to deceive users and trick them into revealing their private information or unintentionally installing harmful applications. As mobile devices are used everywhere, detecting smishing messages has become a very important yet difficult task in cybersecurity. In the present study, the authors conduct a comparative analysis of several deep learning models, namely, the Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi LSTM), Convolutional Neural Network (CNN), and a combination of CNN-LSTM, for the detection of smishing. The experiments are conducted on publicly available SMS datasets, and performance is evaluated using accuracy, precision, recall, F1 Score, and a confusion matrix. The findings indicate that deep learning-based approaches yield significantly better results than traditional methods, with hybrid architectures leading in overall performance.
Keywords: Cybersecurity, Deep Learning, LSTM, Smishing.
Scope of the Article: Computer Science and Engineering