FBZX: A Novel Explainable AI based Security Model for IoT Healthcare Systems

With the rise of IoT in major fields, the risk and need of secure communication has been a question that remains unaddressed. Especially, in healthcare systems, preserving patient data from cyber threats and intruder relics as a significant challenge due to the heterogeneous and dynamic nature of IoT systems. In this paper, a novel and hybrid framework based on Explainable AI (XAI) is proposed which integrates advanced modules like AI-powered Zero Trust Architecture (ZTA), Federated Learning (FL), and Blockchain for enhancing security, decision transparency, and privacy in healthcare systems. The FL technique is used for anomaly detection while Blockchain based identity management prevents spoofing activities and promotes trust in a decentralized environment. Additionally, the infused XAI ensures interpretability and helps in making security decisions. The performance evaluation demonstrates improved threat detection accuracy (98.7%), improved resilience against cyberattacks, and reduced response time (350ms). Overall, this hybrid technique offers a high-end security solution for IoTdriven healthcare infrastructures.