A Deep Learning-Based Framework for Strengthening Cybersecurity in Internet of Health Things (IoHT) Environments

Abstract

The increasing use of IoHT devices in healthcare has brought about revolutionary advancements, but it has also exposed some critical vulnerabilities, particularly in cybersecurity. IoHT is characterized by interconnected medical devices sharing sensitive patient data, which amplifies the risk of cyber threats. Therefore, ensuring healthcare data’s integrity, confidentiality, and availability is essential. This study proposes a hybrid deep learning-based intrusion detection system that uses an Artificial Neural Network (ANN) with Bidirectional Long Short-Term Memory (BLSTM) and Gated Recurrent Unit (GRU) architectures to address critical cybersecurity threats in IoHT. The model was tailored to meet the complex security demands of IoHT and was rigorously tested using the Electronic Control Unit ECU-IoHT dataset. The results are impressive, with the system achieving 100% accuracy, precision, recall, and F1-Score in binary classifications and maintaining exceptional performance in multiclass scenarios. These findings demonstrate the potential of advanced AI methodologies in safeguarding IoHT environments, providing high-fidelity detection while minimizing false positives.