Phishing Detection in IoT Networks Using Machine Learning: A Systematic Review

Torres J.; Guerrero R.; Ticona W. · Lecture Notes in Networks and Systems (2025) · DOI: 10.1007/978-3-031-96775-7_5

Resumen

Phishing detection in Internet of Things (IoT) networks poses a critical challenge in cybersecurity due to the increasing use and vulnerability of such devices. This systematic review aims to identify and analyze existing scientific evidence on the use of Machine Learning and Deep Learning techniques to detect phishing attacks in IoT networks. A total of 126 original articles were collected and evaluated from academic databases, including a manual search, up to June 2024, of which 22 studies met the inclusion criteria. The results indicate that deep learning techniques, such as CNN and RNN techniques, have improved accuracy and precision compared to traditional machine learning techniques. The combination of different approaches has led to improved phishing detection by analyzing complex patterns in network data. In conclusion, advanced machine learning and deep learning techniques offer high levels of effectiveness in detecting phishing in IoT networks, demonstrating their ability to identify anomalous patterns and improve security. Therefore, the implementation of these techniques is crucial to mitigate phishing threats considering the differences in the context and specific characteristics of IoT devices. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Instituciones: Universidad ESAN