Sengan, Sudhakar
Shieh, Chin-Shiuh
Article History
Received: 2 April 2026
Accepted: 29 May 2026
First Online: 6 June 2026
Declarations
:
: The authors declare no competing interests.
: This study did not involve the collection or use of any real patient data or personal health information. All experiments are conducted on publicly available network traffic datasets — IoT-Flock and CICIoT2023 — that contain only simulated or anonymized network flow records with no personally identifiable information. The federated deployment evaluated in this study is a simulation conducted on partitioned versions of these public datasets, and no real institutional data or human subjects are involved. The proposed model is designed in alignment with HIPAA and GDPR principles by ensuring that only model updates, rather than raw data, are transmitted across institutional boundaries, thereby preserving patient privacy through architectural design. Ethical approval was not required for this study.