Leveraging AI for Real-Time Intrusion Detection in IoT-Enabled Healthcare Systems

Abstract

Healthcare has been greatly improved by the rise of the Internet of Medical Things (IoMT). Helps doctors treat patients from a distance. Still, this has meant IoMT systems are concerned with cybersecurity because they are so closely connected. More than ever, they are at risk from cyberattacks. Intrusion Detection System (IDS) systems that are currently in place have a hard time spotting insider threats and controlling the large amount needs and making sure their security measures fit new emerging threats. These issues make the system can lead to dangers for patients and data, showing that we urgently need to improve. what security features are provided for healthcare technology. For this reason, we introduce an innovative intrusion detection framework aiming to improve the detection of threats in the moment in IoMT environments. By breaking up the learning process among several IoMT devices, our method reduces the pressure on single devices and allows the system to adjusted to new needs to the changes in cyber attack techniques. The suitability of the proposed solution is proven using data from IEEE Dataport, including attack datasets and real-time monitoring information, was used. Better results when it comes to finding and identifying targets. The framework presented here not only boosts the security of IoMT devices but also creates more trust in patients the protection of healthcare technologies that are linked.