Robust and Reliable Security Approach for IoMT - Detection of DoS and Delay Attacks through a High-Accuracy Machine Learning Model

Aug 5, 2026

Internet of Medical Things (IoMT) connects medical devices and healthcare systems to the internet, which also exposes them to cyberattacks such as DoS and delay attacks. These threats jeopardize patient safety, data security, and public trust, making early detection essential to avoid harm and service disruptions. The work presents an IoMT network scenario in Omnet++ to capture traffic data, then trains multiple machine learning models for attack detection. An Enhanced Random Forest Classifier for best execution time (ERF-ABE) is proposed to achieve high accuracy and sensitivity with reduced execution time, maintaining strong detection effectiveness while improving runtime efficiency.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Introduction

Internet of Medical Things and security risks

DoS attacks in IoMT

Delay attacks in IoMT

Cyber Attacks and Security Measures

Cyber attacks

Malware attacks (overview)

Robust and Reliable Security Approach for IoMT: Detection of DoS and Delay Attacks through a HighAccuracy Machine Learning Model Abdullah Ali Jawad Al-Abadi1, Mbarka Belhaj Mohamed2, Ahmed Fakhfakh3 1Laboratory of signals, systems, artificial intelligence and networks (SM@RTS), Digital Research Center of Sfax (CRNS), National School of Engineers of Sfax (ENIS) University of Sfax Sfax, Tunisia [abdullah.jawad.1980@gmail.com](abdullah.jawad.1980@gmail.com) 2Laboratory of signals, systems, artificial intelligence and networks (SM@RTS), Digital Research Center of Sfax (CRNS), National School of Engineers of Gabes (ENIG) University of Sfax Gabes, Tunisia [mbarkaenig@gmail.com](mbarkaenig@gmail.com) 3Laboratory of signals, systems, artificial intelligence and networks (SM@RTS), Digital Research Center of Sfax (CRNS), National School of Engineers of Sfax (ENIS) University of Sfax Sfax, Tunisia [ahmed.fakhfakh@enetcom.usf.tn](ahmed.fakhfakh@enetcom.usf.tn) Abstract—Internet of Medical Things (IoMT ) refers to the network of medical devices and healthcare systems that are connected to the internet. However, this connectivity also makes IoMT vulnerable to cyberattacks such as DoS and Delay attacks , posing risks to patient safety, data security, and public trust. Early detection of these attacks is crucial to prevent harm to patients and system malfunctions. In this paper, we address the detection and mitigation of DoS and Delay attacks in the IoMT using machine learning techniques. To achieve this objective, we constructed an IoMT network scenario using Omnet++ and recorded network traffic data. Subsequently, we utilized this data to train a set of common machine learning algorithms. Additionally, we proposed an Enhanced Random Forest Classifier for Achieving the Best Execution Time (ERF-ABE), which aims to achieve high accuracy and sensitivity as well as low execution time for detecting these types of attacks in IoMT networks. This classifier combines the strengths of random forests with optimization techniques to enhance performance. Based on the results, the execution time has been reduced by implementing ERF-ABE, while maintaining high levels of accuracy and sensitivity. Keywords-IoMT; DDoS attack; Delay Attack; Logistic Regression; Random Forest; Decision Tress; Stochastic Gradient Distance; Naive Bayes. I. INTRODUCTION A cyberattack in the IoMT is a malicious attempt to compromise the security and integrity of medical devices and systems that are connected to the internet. IoMT devices include a wide range of medical equipment and wearable devices, such as pacemakers, insulin pumps, blood glucose monitors, and fitness trackers [1] . A cyberattack in IoMT can have severe consequences, including patient harm, loss of sensitive data, financial losses, and damage to public trust. Therefore, it is critical to implement strong cybersecurity measures to protect IoMT devices and systems from potential threats. A DoS attack includes flooding a system or network with traffic or requests, causing the system to slow down or stop working entirely. This type of attack can be dangerous in IoMTif it causes a medical device or system to malfunction, potentially putting the patient's health at risk. For example, if a pacemaker is targeted by a DoS attack, it could stop working altogether, which could be life threatening for the patient. A delay attack involves altering the timing of data transmissions between IoMT devices and networks. This can lead to delays in critical information, which could be detrimental to patient care. For example, a delay in transmitting data from a blood glucose monitor to a healthcare provider could result in apatient's blood sugar levels going unmonitored for an extended period, potentially causing harm. Detecting and mitigating DDoS (Distributed Denial of Service) and Delay Attacks is crucial for ensuring the availability and reliability of online services. Machine lea

FAQs

Why are DoS and delay attacks particularly risky in IoMT?

They can disrupt availability and timing of critical data, potentially causing medical devices to malfunction or delaying vital information delivery. This can directly threaten patient safety and healthcare operations.

How is the IoMT network scenario built and what data is used?

An IoMT network scenario is constructed using Omnet++ and network traffic data is recorded. The recorded traffic data is then used to train machine learning models.

What is ERF-ABE and what improvement does it target?

ERF-ABE is an Enhanced Random Forest Classifier designed to achieve high accuracy and sensitivity while reducing execution time. It combines strengths of random forests with optimization to improve detection performance and runtime efficiency.

Aug 5, 2026

Upload by Olivia Brown