SHIELD: Securing Healthcare IoT with Efficient Machine Learning Techniques for Anomaly Detection
🤖 AI Summary
To address the dual threats of cyberattacks and hardware failures confronting medical Internet-of-Things (IoT) devices, this paper proposes a unified anomaly detection framework capable of jointly identifying malicious network activities and device operational anomalies. Methodologically, we systematically evaluate eight models spanning supervised, semi-supervised, and unsupervised paradigms—including XGBoost, KNN, GAN, VAE, One-Class SVM, Isolation Forest, GNN, and LSTM autoencoder—using real-world medical IoT data. Experimental results demonstrate that XGBoost achieves the best overall performance with 99% accuracy and only 0.04-second inference latency; KNN attains near-perfect attack detection accuracy with merely 0.05-second latency. To our knowledge, this is the first systematic, multi-paradigm comparative study of anomaly detection models in medical IoT settings. Our findings empirically validate the superiority of lightweight tree-based models in terms of accuracy, computational efficiency, and edge-deployment feasibility—providing a practical, high-reliability, low-latency solution for edge-level security monitoring in clinical environments.
Application Category
📝 Abstract
The integration of IoT devices in healthcare introduces significant security and reliability challenges, increasing susceptibility to cyber threats and operational anomalies. This study proposes a machine learning-driven framework for (1) detecting malicious cyberattacks and (2) identifying faulty device anomalies, leveraging a dataset of 200,000 records. Eight machine learning models are evaluated across three learning approaches: supervised learning (XGBoost, K-Nearest Neigh-bors (K- NN)), semi-supervised learning (Generative Adversarial Networks (GAN), Variational Autoencoders (VAE)), and unsupervised learning (One-Class Support Vector Machine (SVM), Isolation Forest, Graph Neural Networks (GNN), and Long Short-Term Memory (LSTM) Autoencoders). The comprehensive evaluation was conducted across multiple metrics like F1-score, precision, recall, accuracy, ROC-AUC, computational efficiency. XGBoost achieved 99% accuracy with minimal computational overhead (0.04s) for anomaly detection, while Isolation Forest balanced precision and recall effectively. LSTM Autoencoders underperformed with lower accuracy and higher latency. For attack detection, KNN achieved near-perfect precision, recall, and F1-score with the lowest computational cost (0.05s), followed by VAE at 97% accuracy. GAN showed the highest computational cost with lowest accuracy and ROC-AUC. These findings enhance IoT-enabled healthcare security through effective anomaly detection strategies. By improving early detection of cyber threats and device failures, this framework has the potential to prevent data breaches, minimize system downtime, and ensure the continuous and safe operation of medical devices, ultimately safeguarding patient health and trust in IoT-driven healthcare solutions.
Problem
Research questions and friction points this paper is trying to address.
Detecting malicious cyberattacks in healthcare IoT systems
Identifying faulty device anomalies using machine learning
Evaluating multiple ML models for security and reliability
Innovation
Methods, ideas, or system contributions that make the work stand out.
Uses supervised, semi-supervised, and unsupervised learning models
Evaluates eight ML models for anomaly and attack detection
Leverages XGBoost and KNN for high accuracy and efficiency
🔎 Similar Papers
No similar papers found.
