MODELLING CYBERATTACK VECTORS AND METHODS FOR ENSURING THE CYBER RESILIENCE OF MULTI-LEVEL CONTINUOUS CARDIAC MONITORING SYSTEMS

This project looks at security weaknesses in Internet of Medical Things (IoMT) systems, with a focus on multi‑level, continuous cardiac monitoring setups. Conventional signature‑based defenses and heavyweight cryptographic methods often don’t work well in medical sensor networks that have limited resources, because they add latency and require a lot of computation. To overcome these problems, we propose a hybrid edge‑based intrusion detection system (Edge‑IDS). The Edge‑IDS protects the hidden feature space of cardiac signals from semantic tampering and cyber‑physical attacks. It combines a Variational Autoencoder (VAE) with a Deep Convolutional Neural Network (DCNN) to pull out strong features and spot anomalies. We tune the model’s hyperparameters with the Archimedes Optimization

Algorithm (AOA), which improves detection accuracy and cuts down false alarms. Placing this optimized model at the network edge gives continuous cyber‑resilience while still meeting the real‑time processing needs of cardiac telemetry. The guide that follows helps engineering students set up, simulate, and test this hybrid machine‑learning architecture using either synthetic data or publicly available electrocardiogram (ECG) datasets. It provides a solid starting point for building secure, resource‑efficient biomedical monitoring systems.

Message: Hi FE, I need help with “MODELLING CYBERATTACK VECTORS AND METHODS FOR ENSURING THE CYBER RESILIENCE OF MULTI-LEVEL CONTINUOUS CARDIAC MONITORING SYSTEMS” in “Biotechnology & Biomedical Engineering”