Authors : Muzammil Sunusi Umar; Dr. Sandeep Kumar; Muhammad Ibrahim Isah; Bello Bello Musa; Usman Ibrahim Usman; Abdurrazaq Jibril Baba

Volume/Issue : Volume 11 - 2026, Issue 6 - June

Google Scholar : https://tinyurl.com/3h8v5wnp

Scribd : https://tinyurl.com/6dfajrpf

DOI : https://doi.org/10.38124/ijisrt/26jun010

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The increasing dependency on mobile connectivity has turned smishing attacks into a significant cybersecurity threat which leads the stealing of sensitives financial and credential information by using some modern technique and tools likes phishing through content injection and social engineering. This research employs a hybrid machine learning technique to create an intelligent web-based system for classifying smishing, spam, and legitimate SMS messages. To enhance detection capabilities, the study implements a supervised learning approach with various classifiers, including Naïve Bayes, Support Vector Machine, Random Forest, and Logistic Regression, all of which are combined through an hybrid machine learning strategy. The preprocessing and transforming of SMS data are publicly available. Also, the research used TF- IDF and N-gram feature extraction methods. The proposed method was evaluated using multi- class classification metrics and achieved accuracy of 97.58% and F1-score of 97.58%. Experimental results justify that the hybrid ensemble model smashed specific classifiers, getting consistent performance and high accuracy over all three categories. The system best at identifying deceptive SMS messages by its notable recall rate for smishing content. To confirm the whole user experience and allow for automated SMS detection, a classification model was integrated into a web-based platform. The hybrid machine learning technique gives a dependable approach for identifying the SMS threats that confirm by the results. The research also plays a vital role in the field of cybersecurity and forensics by presenting an intelligent smishing and phishing detection.

Keywords : Cybersecurity, Smishing, Phishing, Hybrid Machine Learning, SMS Security, Text Classification.

References :

1. Altan, I., Bachir, A., Parbhulkar, Y., Rizvi, A.M., Farazi, M., 2025. Dual-Path Phishing Detection: Integrating Transformer-Based NLP with Structural URL Analysis. https://doi.org/10.48550/arXiv.2509.20972
2. Aparna, D.G., Krishna, B.V., Reddy, C.K., Latha, K., Akshitha, M., 2025. SMS PHISHING DETECTION USING MACHINE LEARNING TECHNIQUES 10.
3. Cagatay Catal, Gorkem Giray, Bedir Tekinerdogan, Sandeep Kumar, Suyash Shukla, n.d. Applications of deep learning for phishing detection: a systematic literature review | Knowledge and Information Systems | Springer Nature Link [WWW Document]. URL https://link.springer.com/article/10.1007/s10115-022-01672-x (accessed 2.9.26).
4. Chichwadia, A.E., Mpekoa, N., 2024. Detecting Smishing and Vishing Attacks using Machine Learning. Int. J. Intell. Comput. Res. 15, 1234–1241. https://doi.org/10.20533/ijicr.2042.4655.2024.0151
5. Elbehiery, H., 2025. An Efficient Phishing Detection Framework Based on Hybrid Machine Learning Models. Sustain. Mach. Intell. J. 11. https://doi.org/10.61356/SMIJ.2025.11525
6. Goel, D., Ahmad, H., Jain, A.K., Goel, N.K., 2024. Machine Learning Driven Smishing Detection Framework for Mobile Security [WWW Document]. arXiv.org. URL https://arxiv.org/abs/2412.09641v1 (accessed 2.9.26).
7. Ishaq, A., Iro, Z., Musa, A., Ayuba, A., Maijamaa, B., Miyim, A., 2025. An Enhanced Hybrid CNN-LSTM with Attention Mechanism for SMS Phishing Detection.
8. Jain, A.K., Gupta, B.B., 2018. Rule-based framework for detection of smishing messages in mobile environment. Procedia Comput. Sci. 125, 617–623.
9. Kumar, V., Parmar, P., Singh, V., Kumar, S., Pawar, P., 2025. Phishing URL Detection Using Machine Learning: Harnessing Data Analysis to Strengthen Cyber Security. pp. 361–378. https://doi.org/10.1007/978-981-96-6715-4_26
10. Mahendru, S., Pandit, T., 2024. SecureNet: A Comparative Study of DeBERTa and Large Language Models for Phishing Detection, in: 2024 IEEE 7th International Conference on Big Data and Artificial Intelligence (BDAI). pp. 160–169. https://doi.org/10.1109/BDAI62182.2024.10692765
11. Mahmud, T., Prince, M.A.H., Ali, M.H., Hossain, M.S., Andersson, K., 2024.
12. Enhancing Cybersecurity: Hybrid Deep Learning Approaches to Smishing Attack Detection. Systems 12, 490. https://doi.org/10.3390/systems12110490
13. Munoz, M., Islam, M., 2025. A Balanced Dataset for Spam and Smishing Detection using Large Language Models (LLMs) 1. https://doi.org/10.17632/vmg875v4xs.1
14. Rajput, Y., Mishra, K., 2025. The Evolution of SMS Phishing (Smishing) Detection: A Comprehensive Review of Heuristic, Machine Learning and Natural Language Processing Techniques. Appl. Sci.
15. Rao, R.S., Kondaiah, C., Pais, A.R., Lee, B., 2025. A hybrid super learner ensemble for phishing detection on mobile devices. Sci. Rep. 15, 16839. https://doi.org/10.1038/s41598-025-02009-8
16. Saidat, M.R.A., Yerima, S.Y., Shaalan, K., 2024. Advancements of SMS Spam Detection: A Comprehensive Survey of NLP and ML Techniques. Procedia Comput. Sci., 6th International Conference on AI in Computational Linguistics 244, 248–259. https://doi.org/10.1016/j.procs.2024.10.198
17. Tamal, M.A., Islam, M.K., Bhuiyan, T., Sattar, A., Prince, N.U., 2024. Unveiling suspicious phishing attacks: enhancing detection with an optimal feature vectorization algorithm and supervised machine learning. Front. Comput. Sci. 6. https://doi.org/10.3389/fcomp.2024.1428013
18. Vennela, A., Akarapu, R.B., Rakshith, B.L., Asirvatham, L.G., Sunil, G., 2026.
19. Intelligent cybersecurity systems for phishing attack detection - An overview. Comput. Electr. Eng. 130, 110829. https://doi.org/10.1016/j.compeleceng.2025.110829
20. Xu, H., Qadir, A., Sadiq, S., 2025. Malicious SMS detection using ensemble learning and SMOTE to improve mobile cybersecurity. Comput. Secur. 154, 104443. https://doi.org/10.1016/j.cose.2025