CryptoDNA: A Machine Learning Paradigm for DDoS Detection in Healthcare IoT, Inspired by crypto jacking prevention Models

TL;DR

CryptoDNA tackles DDoS threats in healthcare IoT/IoM by adopting cryptojacking-inspired, lightweight behavioral analytics. It combines entropy-based traffic analysis with time-series monitoring and a dual-model setup (pruned Random Forest and Autoencoder) to detect both known and zero-day attacks, optimized for edge devices. Trained on synthetic and real-world data such as CICDDoS2019, it achieves a reported accuracy of $96.8\%$ and a false positive rate of $2.1\%$, while maintaining scalable latency and resource efficiency. The work demonstrates strong practical impact for securing critical healthcare infrastructures and illustrates the value of cross-domain ideas in adaptive cybersecurity defenses for healthcare environments.

Abstract

The rapid integration of the Internet of Things (IoT) and Internet of Medical (IoM) devices in the healthcare industry has markedly improved patient care and hospital operations but has concurrently brought substantial risks. Distributed Denial-of-Service (DDoS) attacks present significant dangers, jeopardizing operational stability and patient safety. This study introduces CryptoDNA, an innovative machine learning detection framework influenced by cryptojacking detection methods, designed to identify and alleviate DDoS attacks in healthcare IoT settings. The proposed approach relies on behavioral analytics, including atypical resource usage and network activity patterns. Key features derived from cryptojacking-inspired methodologies include entropy-based analysis of traffic, time-series monitoring of device performance, and dynamic anomaly detection. A lightweight architecture ensures inter-compatibility with resource-constrained IoT devices while maintaining high detection accuracy. The proposed architecture and model were tested in real-world and synthetic datasets to demonstrate the model's superior performance, achieving over 96% accuracy with minimal computational overhead. Comparative analysis reveals its resilience against emerging attack vectors and scalability across diverse device ecosystems. By bridging principles from cryptojacking and DDoS detection, CryptoDNA offers a robust, innovative solution to fortify the healthcare IoT landscape against evolving cyber threats and highlights the potential of interdisciplinary approaches in adaptive cybersecurity defense mechanisms for critical healthcare infrastructures.

Figures (8)

• Figure 1: Global Average Attack by Industry.
• Figure 2: Attacked Healthcare Organization.
• Figure 3: Traditional Intrusion Detection Framework with ML Models aguru2024lightweight.
• Figure 4: Example of a blockchain based Secure IoT System Identity Management system, inspired by s22197535.
• Figure 5: Example of Federated Learning Process in IoT Networks. inspired by alhasawi2024federated.