Hybrid and adaptive framework for secure and scalable authentication in healthcare IoT

The rapid adoption of Internet of Things (IoT) in Healthcare has significantly enhanced real-time patient monitoring and decision making. However, security and privacy still remain the major concern due to sensitive medical data of patients especially on low-power IoT devices. Traditional authentication schemes like Zero Knowledge Proof (ZKP) and Elliptic Curve Cryptography (ECC) often struggle with efficiency in resource-constraint environments due to their computational overhead. In order to address these challenges, we propose a Neural-Based Hybrid and Adaptive Framework that combines Schnorr ZKP with Kyber-based key encapsulation, using a neural network to dynamically select Kyber variants (512, 768, 1024) based on device parameters (type, authentication time, transmission time) to balance security and efficiency for low-power IoT devices. Extensive experiments validated robust security against replay and spoofing attacks, achieving authentication success for legitimate clients and zero attack successes. Furthermore, our proposed framework outperforms traditional Kyber1024 and ZKP/ECC based authentication schemes in terms of authentication time and computational overhead making it robust and scalable solution for sensitive and resource-limited environments like HealthCare IoT systems. • Design a novel hybrid authentication framework that integrates ZKP and Kyber PQC (Post Quantum Cryptography) to ensure secure and efficient authentication for IoT healthcare devices. • Utilize Neural Network to intelligently select the most appropriate Kyber variant based on threat level and computational efficiency. • Provide comprehensive experimental analysis comparing the proposed hybrid and adaptive framework with traditional ZKP, ECC and static Kyber implementations.