The Future of Smishing Prevention: Integrating AI and IoT Mobile Network Security

By: Mosiur Rahaman, International Center for AI and Cyber Security Research and Innovation, Asia University, Taiwan

ABSTRACT

As cellular phones become increasingly important in daily life, there is no doubt that attackers can have a pick of interest in this and make it a target of attack. Smishing, a type of phishing that scams people by sending text messages, has emerged as a significant threat in cybersecurity. Traditional strategies and using anti-smishing tools like applications fall short against various ways of these attacks. The rapid evolution of Artificial Intelligence (AI) and the Internet of Things (IoT) has been the bright side that most researchers have seen to prevent smishing in the future. By examining how smishing, AI, and IoT work, this article aims to provide insights into smishing, AI, how AI can detect smishing messages, the future of AI in stopping smishing, what is IoT, how IoT can improve mobile security, and how AI and IoT can work together to stop smishing.

INTRODUCTION

The world is developing into a more technical and advanced one, and with the advent of technology, the methods of the scammers on fooling people were also upgraded. According to the Mobile phone Usage Statistics (2024) published by Supply Gem [1] at the end of 2023 the number of smartphone users is around 6.8 billion, and beyond 2023, the current data trend suggests that there will be roughly 7 billion users by the end of 2024 and 7.5 billion by the end of 2026.

A graph of a number of people

Description automatically generated with medium confidence
Figure 1:Smartphone Users Growth (Pink Colored Graph Indicates Estimation)

Since almost everyone uses a cell phone for their work, smishing has become personal and a big threat now. The ever-evolving landscape of cyber threats requires a proactive and adoptable approach to cybersecurity. Artificial Intelligence (AI) has emerged as a transformative force in this domain, where it provides unprecedented capabilities for threat detection, risk assessment, and incident response [2]. The purpose and scope of this article is to discuss the future of smishing prevention, where it also ventures the idea of ​​integrating AI and IoT for mobile network security.

OVERVIEW OF SMISHING

Smishing is a social engineering attack that uses fake mobile text messages to trick people into downloading malware, sharing sensitive information, or sending money to cybercriminals [3]. Smishing texts may appear in various forms, they can disguise themselves as a legit bank, your internet service provider, a company, organization, group, or family, aligned with the contents that were designed to make the recipient react mostly in a not normal way, as it may contain emotional triggers, urgency, fake rewards, or opportunities that were too good to be true [4]. Figure 2 shows the attack mechanism of Smishing.

A diagram of a computer

Description automatically generated
Figure 2:Smishing Attack Mechanism

Smishing is a well-known type of cybercrime which according to the 2024 Proofpoint state of phish report, in 2023 71% of organizations have experienced at least one successful phishing attack compared to only 84% in 2022, but the consequences of successful attack is even more severe because the increase in the report of financial penalties is 144% and there is a 50% increase in reports of damage to their reputation [5]. Figure 3 shows an example of a Smishing attack.

A screenshot of a message

Description automatically generated
A screenshot of a phone

Description automatically generated
A screenshot of a phone

Description automatically generated
Figure 3:Smishing Text Samples

AI AND IOT IN SMISHING

Artificial Intelligence researchers have devoted their time to find techniques to identify and detect smishing messages, these techniques have included machine learning and deep learning methods with the combination of natural language processing [6]. The emergence of machine learning in this big information era have become one of the vital parts in solving this case, they played a vital role in mitigating, identifying, and analyzing cyberthreats in real-time, because information drives this method and if massive number of accurate information is generated in real-time, the machine learning algorithms can use this to detect abnormal patterns and detect potential harmful activities happening in your system [7]. The use of AI in solving this problem becomes one of the brighter sides in the advent of technology, AI driven solutions offer a lot of positive impact such as the automation of smishing detection. With the help of machine learning where it can be identified as a subset of AI, these theories become handy and are achievable, as training machine learning algorithms with a vast amount of accurate data allows it to identify threats in high accuracy.

A diagram of a chat

Description automatically generated
Figure 4:The Use of AI in Smishing Detection

Internet of Things (IoT) devices have paved the way of making things connected possible, it is now one of the rapidly growing technologies that makes the life of a person easy. IoT’s trademark has been making things connected, and speaking of making things connected it becomes one of the prominent attack targets of the hacker making it one of the major flaws of IoT. Due to the advanced tactics of hackers in penetrating this technology, researchers continuously find a way in developing a mechanism to combat attackers in IoT devices, many real-world IoT approaches have already been used to solve this problem. Some examples of it are the use of Data Mining, Deep learning, and Machine based learning approach that was already mentioned earlier, these approach enables the detection of smishing attacks allowing dynamic adaptation of new scammer strategies that lowers their chance in penetrating your device [8].

CONCLUSION

SMS phishing, or smishing, is one of the most common scams in today’s modern world. With the advent of technology and the wide use of cellular phones in transactions and daily work, scammers have found these devices to be one of their main targets to fool people. With the raised problem, some prevention mechanisms, such as the anti-smishing tools, were not sufficient to solve it, that is why another mechanism that includes software and physical understanding of the messages sent to the user was needed in order for this attack to be avoided. On the bright side, AI’s machine learning algorithms, and IoT mobile network security can be integrated to prevent smishing. The mechanism will be combining IoT into different machine learning architectures that would make the detection of the smishing messages more accurate and filter the detected messages in different folders that will clearly describe the contents inside, such as scam or smish. The integration of AI and IoT will leverage the mechanism of smishing detection in the modern era, with this method the lax of IoT in terms of security will be compensated by the AI approaches which will make it successful in this area. AI and IoT is a wide and complex topic with a lot of useful methods and algorithms that was waiting to be explored, in this paper we only tackle about some algorithms and methods that can be used, it is recommended to explore more on the possible integration of deep learning models for enhanced smishing detections and possible denial of spam messages in real-time.

REFERENCES

  1. 39 Mobile Phone Usage Statistics & Data (2025 Research).” Accessed: Feb. 04, 2025. [Online]. Available: https://supplygem.com/publications/mobile-phone-usage-statistics/
  2. S. P. Pattyam, “Artificial Intelligence in Cybersecurity: Advanced Methods for Threat Detection, Risk Assessment, and Incident Response,” Journal of AI in Healthcare and Medicine, vol. 1, no. 2, Art. no. 2, Sep. 2021.
  3. E. Blancaflor, M. A. Romero, I. Nacu, and D. R. Golosinda, “A Case Study on Smishing: An Assessment of Threats against Mobile Devices,” in Proceedings of the 2023 9th International Conference on Computer Technology Applications, in ICCTA ’23. New York, NY, USA: Association for Computing Machinery, Aug. 2023, pp. 172–178. doi: 10.1145/3605423.3605446.
  4. 2024 State of Phish Report – Impact of Human Behavior | Proofpoint US,” Proofpoint. Accessed: Feb. 04, 2025. [Online]. Available: https://www.proofpoint.com/us/blog/security-awareness-training/2024-state-of-phish-report
  5. R. E. Ulfath, I. H. Sarker, M. J. M. Chowdhury, and M. Hammoudeh, “Detecting Smishing Attacks Using Feature Extraction and Classification Techniques,” in Proceedings of the International Conference on Big Data, IoT, and Machine Learning, M. S. Arefin, M. S. Kaiser, A. Bandyopadhyay, Md. A. R. Ahad, and K. Ray, Eds., Singapore: Springer, 2022, pp. 677–689. doi: 10.1007/978-981-16-6636-0_51.
  6. K. D. O. Ofoegbu, O. S. Osundare, C. S. Ike, O. G. Fakeyede, and A. B. Ige, “Real-Time Cybersecurity threat detection using machine learning and big data analytics: A comprehensive approach,” Computer Science & IT Research Journal, vol. 4, no. 3, Art. no. 3, Dec. 2023, doi: 10.51594/csitrj.v4i3.1500.
  7. H. N. Fakhouri, B. Alhadidi, K. Omar, S. N. Makhadmeh, F. Hamad, and N. Z. Halalsheh, “AI-Driven Solutions for Social Engineering Attacks: Detection, Prevention, and Response,” in 2024 2nd International Conference on Cyber Resilience (ICCR), Feb. 2024, pp. 1–8. doi: 10.1109/ICCR61006.2024.10533010.
  8. A review of phishing attacks and countermeasures for internet of things‐based smart business applications in industry 4.0”, doi: 10.1002/hbe2.301.
  9. Navaneeth J. (2024) Building Robust Phishing Detection Systems with Deep Learning, Insights2Techinfo, pp.1

Cite As

Rahaman M. (2025) The Future of Smishing Prevention: Integrating AI and IoT Mobile Network Security, Insights2Techinfo, pp.1

81280cookie-checkThe Future of Smishing Prevention: Integrating AI and IoT Mobile Network Security
Share this:

Leave a Reply

Your email address will not be published.