| Abstract | The Internet of Things (IoT) is transforming society by connecting businesses and optimizing systems across industries. Its impact has been felt in healthcare, where it has the potential to revolutionize medical treatment. Conversely, healthcare systems are targeted by attackers and security threats. Malicious activities against such systems intend to compromise privacy and acquire control over internal procedures. In this regard, advanced analytics can enhance these attacks’ detection, mitigation, and prevention and improve overall IoT security. However, the process of producing realistic datasets is complex. There are critical aspects to consider when developing models that can be directly deployed in real environments (e.g., multiple devices, features, and realistic testbed). Thereupon, the main goal of this research is to conduct a review of Machine Learning (ML) solutions for IoT security in healthcare. Furthermore, this review is conducted from a dataset standpoint, focusing on existing datasets, resources, applications, and open challenges. Our primary objective is to highlight the current landscape of datasets for IoT security in healthcare and the immediate requirements for future datasets to support the development of novel approaches. |
|---|
