AI-driven Threat Management in Healthcare Systems
Ismaila Sy, Birahime Diouf, Abdou Khadre Diop, Cyril Drocourt, David Durand · River Publishers eBooks · 2025
This chapter delves into the critical realm of securing interconnected medical Internet of Things (IoMT) networks by employing a sophisticated deep learning-based anomaly detection approach. The research utilizes datasets such as UNSW-NB15 and the IoT-specific EdgeILIoT dataset, employing a range of deep learning models including the multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM), and the amalgamation of CNN-LSTM. The primary focus is on achieving precision in detecting security threats and minimizing false positives. Through extensive experiments on real-world medical IoT network data, the approach demonstrates exceptional precision rates, emphasizing its efficacy in accurately identifying anomalies within the complex network fabric. Additionally, the chapter addresses the consequences of cyberattacks in the healthcare domain, highlighting the imperative of robust security measures in the ever-evolving digital healthcare landscape. The findings contribute to ongoing efforts to strengthen security measures, providing an innovative solution to mitigate security risks in IoMT environments and improve the overall quality of healthcare delivery.