Edge-Based Secure Authentication and Anomaly Detection Framework for Wearable IoT in Healthcare Systems

Wearable technology is essential for rapidly acquiring data and monitoring patients in the swiftly advancing field of smart healthcare. The growing number of cyberattacks and privacy violations, coupled with limited resources, compels enterprises to develop robust security frameworks. This article examines a lightweight, edge-enabled security architecture for wearables used in medical settings. This framework utilizes safe data aggregation and homomorphic encryption to enhance system performance and improve data security. A thin convolutional neural network (CNN) detects risks in real time at the periphery, including malfunctioning sensors or anomalous physiological data. A context-aware multi-factor authentication (MFA) system restricts access to critical data to those in proximity. This system uses biometric identification, dynamic contextual information (e.g., geolocation and usage patterns), and one-time passwords (OTPs). These results indicate that the solution protects user confidence, ensures data privacy, and secures wearable healthcare IoT environments.