Current Smishing & Vishing Phenomena: A Systematic Review of Text Message & Phone Attack Models
Abstract
Smishing and vishing are forms of phishing attacks conducted through text messages (SMS) and voice calls. Alongside the growing use of mobile devices, these two types of attacks have become increasingly common and harder to detect. This study aims to conduct a systematic review of recent scientific literature discussing the phenomena of smishing and vishing, particularly from the perspective of attack models and detection approaches. Using the Systematic Literature Review (SLR) method, ten scientific articles published between 2019 and 2025 were critically analyzed. The study found that most smishing detection methods leverage machine learning and deep learning techniques, with models such as Support Vector Machine, Random Forest, and BERT-CNN demonstrating high performance. Meanwhile, approaches to vishing remain limited, generally involving only call metadata analysis or voice pattern based detection. This study also identified key challenges including the lack of local datasets, minimal research focus on vishing, and low real-world implementation of detection technologies. Future research recommendations include the development of open datasets, integration of detection systems on mobile devices, and increased user awareness through digital education.
References
L. Ulfa, N. Kurniawati, and Y. Andriani, "Kesadaran Keamanan Informasi atas Phising, Smishing, dan Vishing pada Warga Kota Cimahi," Jurnal Ilkom, vol. 16, no. 1, pp. 10–19, 2024.
A. E. Chichwadia and N. Mpekoa, "Detecting Smishing and Vishing Attacks using Machine Learning," Int. J. of Digital Society and Data
Engineering, vol. 14, no. 3, pp. 1–10, 2024.
Thesai.org, "SmishGuard: Leveraging Machine Learning and NLP for Smishing Detection," IJACSA, vol. 14, no. 11, pp. 372–379, 2022.
R. M. Amin and S. Majid, "Review of Smishing Detection via Machine Learning," Iraqi Journal for Computer Science, vol. 23, no. 2, pp. 55–65, 2023.
A. Shaikh, M. Shaikh, and S. R. Khan, "Smishing Detection using Machine Learning for SMS Phishing Attacks," IJITEE, vol. 14, no. 5, pp.
130–136, 2025.
University of Valladolid, "Towards Multi-Class Smishing Detection: Feature Vector Approach," CEUR Workshop Proc., vol. 3432, 2024.
R. Hosseinpour and A. Das, "Multi-Signal Model for Detecting Evasive Smishing," arXiv preprint arXiv:2505.18233, 2025.
G. Tanbhir, A. Rahman, and R. Hasan, "Hybrid ML Model for Bangla Smishing Text using BERT-CNN," arXiv preprint arXiv:2502.01518,
2025.
D. Goel, A. Gaur, and P. Jain, "ML-Driven Smishing Detection Framework for Mobile Security," arXiv preprint arXiv:2312.13428, 2024.
A. M. Shibli, T. Ahmed, and N. Islam, "AbuseGPT: Generative AI for Smishing Campaigns," arXiv preprint arXiv:2402.12320, 2024.
Helmiawan, M. A., & Wiharko, T. (2018). Application of Fingerprint Security System on Motorcycles using Arduino Microcontroller. J-Tin’s-Jurnal Teknik Informatika, 2(1).
Helmiawan, M. A., Juna, D. I., & Ramdhani, B. (2018). Pengamanan Sistem Dan Data E-Voting Berbasis Network. INTERNAL (Information System Journal), 1(1), 1–10.
Helmiawan, M. A., Firmansyah, E., Fadil, I., Sofivan, Y., Mahardika, F., & Guntara, A. (2020). Analysis of web security using open web application security project 10. 2020 8th International Conference on Cyber and IT Service Management
Helmiawan, M. A., Julian, E., Cahyan, Y., & Saeppani, A. (2021). Experimental evaluation of security monitoring and notification on network intrusion detection system for server security. 2021 9th International Conference on Cyber and IT Service Management (CITSM ….
Helmiawan, M. A., Fadil, I., Sofiyan, Y., & Firmansyah, E. (2021). Security model using intrusion detection system on cloud computing security management. 2021 9th International Conference on Cyber and IT Service Management (CITSM ….
Helmiawan, M. A., & Nasution, A. I. (2022). The Effect of Internet Banking Use and Customer Protection Against Cyber Crime at Bank Rakyat Indonesia. Journal of Islamic Economics and Business, 2(2), 170–183.