Detection of Temporal Interference in Medical IoT Sensor Networks

The increasing adoption of Medical Internet of Things (MIoT) technologies is transforming healthcare through continuous, real-time patient monitoring, (Alsolami, et al 2024). From wearable sensors to critical care devices, these systems underpin time-sensitive clinical decision making. However, their reliance on low power, resource-constrained hardware introduces significant vulnerabilities (Reed, et al 2025).

In medical IoT environments where sensitive data is being transmitted, even minimal disruption to data streams such as delays, jitter, or subtle inconsistencies can have serious consequences. Malicious actors may introduce temporal interference, which is particularly challenging to detect, as it often mimics legitimate variations in IoT sensor behaviour. As a result, conventional security and anomaly detection techniques are ineffective or impractical, especially those requiring computationally intensive methods such as deep packet inspection or large-scale data processing. (Reed et al 2024)

This PhD project will investigate lightweight, real-time anomaly detection tailored to highly constrained medical IoT systems. The research will focus on identifying subtle temporal disruptions in the transmission of sensor data while ensuring low computational overhead, interpretability, and suitability for real-time analysis.

Objectives

Critically evaluate current state of the art approaches to anomaly detection in IoT and medical sensing systems

Develop or curate a dataset capturing realistic temporal behaviour of IoT sensor data, including scenarios such as slow and low-rate denial of service attacks.

Design and implement a lightweight detection framework capable of accurately identifying subtle temporal anomalies in real time where resource constraints mandate a lightweight solution.

Skills Required:

Network Communications technologies, Cyber Security, Network management and analysis

Background Reading:

Reed, A., Dooley, L., & Mostefaoui, S. K. (2025). SA-IDS: A Single Attribute Intrusion Detection System for Slow DoS attacks in IoT Networks. Internet of Things, 30, 101512. https://doi.org/10.1016/j.iot.2025.101512

Reed, A., Dooley, L., & Mostefaoui, S. K. (2024). The Guardian Node Slow DoS Detection Model for Real-Time Application in IoT Networks. MDPI Sensors, 24(17), 5581. https://doi.org/10.3390/S24175581

Alsolami, T., Alsharif, B. and Ilyas, M. (2024), ‘Enhancing Cybersecurity in Healthcare: Evaluating Ensemble Learning Models for Intrusion Detection in the Internet of Medical Things’, Sensors 24(18), NA–NA.

Contact