Elliptic Curve Enhanced Neural Encryption Models for Privacy Preservation in Smart Healthcare

Abstract

The rapid digitization of healthcare systems has led to the widespread adoption of smart healthcare technologies, including wearable devices, remote patient monitoring systems, and IoT-enabled medical infrastructures. However, the sensitive nature of medical data raises critical concerns regarding privacy, security, and unauthorized access. Traditional encryption methods often struggle to balance computational efficiency and strong cryptographic security in resource-constrained healthcare environments. This study proposes an Elliptic Curve Enhanced Neural Encryption Model (ECENEM) for privacy preservation in smart healthcare systems. The proposed framework integrates Elliptic Curve Cryptography (ECC) for lightweight and secure key generation with deep neural networks for adaptive encryption pattern learning and anomaly-resistant secure communication. The model enhances privacy protection by combining mathematical cryptographic strength with AI-driven dynamic encryption behavior. Performance is evaluated using encryption strength, computational overhead, latency, and security resistance against common attacks. Experimental results demonstrate that the proposed model achieves higher security efficiency with lower computational cost compared to conventional encryption techniques.