A Framework for Malicious Traffic Detection in IoT Healthcare Environment

Area of Science:

• Cybersecurity
• Computer Science
• Network Security

Background:

• The Internet of Things (IoT) has revolutionized daily life, enabling smart devices and systems across various domains.
• IoT security is a critical concern, particularly in healthcare, due to the unique vulnerabilities of resource-constrained devices and distinct protocols.
• Existing security solutions are often inadequate for IoT environments, necessitating specialized tools and methods.

Purpose of the Study:

• To propose a framework for developing IoT context-aware security solutions.
• To introduce IoT-Flock, an open-source tool for generating normal and malicious IoT traffic for research.
• To create an IoT healthcare dataset for detecting cyber-attacks and enhancing system security.

Main Methods:

• Development of IoT-Flock, an open-source IoT data generator tool.
• Creation of a utility to convert captured traffic into an IoT dataset.
• Generation of an IoT healthcare dataset comprising normal and attack traffic.
• Application of machine learning techniques for cyber-attack detection.

Main Results:

• A novel framework for developing IoT context-aware security solutions has been established.
• An open-source tool (IoT-Flock) and a utility for dataset generation are provided.
• A comprehensive IoT healthcare dataset was created, facilitating attack detection research.
• Machine learning models demonstrated effectiveness in identifying cyber-attacks within the generated dataset.

Conclusions:

• The proposed framework and tools aid in creating specialized security solutions for IoT environments.
• The developed IoT healthcare dataset is valuable for advancing research in IoT security, especially for sensitive applications.
• This work contributes to enhancing the security posture of IoT healthcare systems against emerging cyber threats.