Noise-Driven AI Sensors: Secure Healthcare Monitoring with PUFs

TL;DR

This paper presents a noise-driven platform that enhances security and robustness of healthcare sensors using PUFs and ML, achieving high accuracy, security, and low power consumption for wearable medical devices.

Contribution

It introduces a novel approach combining hardware noise, PUF-based security, and ML for secure, low-power healthcare monitoring devices, addressing multiple challenges simultaneously.

Findings

Noise improves ML accuracy by 8% (92% for PVCs and AF)

PUFs achieve 98% uniqueness for security

System operates within 50 uW power budget

Abstract

Wearable and implantable healthcare sensors are pivotal for real-time patient monitoring but face critical challenges in power efficiency, data security, and signal noise. This paper introduces a novel platform that leverages hardware noise as a dual-purpose resource to enhance machine learning (ML) robustness and secure data via Physical Unclonable Functions (PUFs). By integrating noise-driven signal processing, PUFbased authentication, and ML-based anomaly detection, our system achieves secure, low-power monitoring for devices like ECG wearables. Simulations demonstrate that noise improves ML accuracy by 8% (92% for detecting premature ventricular contractions (PVCs) and atrial fibrillation (AF)), while PUFs provide 98% uniqueness for tamper-resistant security, all within a 50 uW power budget. This unified approach not only addresses power, security, and noise challenges but also enables scalable, intelligent sensing for telemedicine and IoT applications.