EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

End-to-End Privacy-Aware Federated Learning for Wearable Health Devices via Encrypted Aggregation in Programmable Networks

Huzaif Khan, Rahul Kavati iD, Sriven Srilakshmi Pulkaram, Ali Jalooli iD

Sensors · 17.11.2025 · 25 (22) · 7023

DOI: 10.3390/s25227023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 17.11.2025. Verfasst von Huzaif Khan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, California State University Dominguez Hills, 1000 E. Victoria Street, Carson, CA 90747, USA. Hauptthemen laut MEDLINE: Wearable Electronic Devices, Computer Security. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The widespread use of wearable Internet of Things (IoT) devices has transformed modern healthcare through the real-time monitoring of physiological signals. However, real- time responsiveness and data privacy are big challenges. Federated Learning (FL) keeps direct data exposure to a minimum but is susceptible to inference attacks on model updates and heavy communication overhead. In-network computing (INC) solutions currently offer greater efficiency but without cryptographic security, whereas homomorphic encryption (HE) offers high privacy but at the expense of latency and scalability. To bridge this gap, we present Edge-Assisted Homomorphic Federated Learning (EAH-FL), a framework that unifies Cheon–Kim–Kim–Song (CKKS) HE with in-network aggregation. Lightweight clients outsource encryption and decryption to trusted edge devices, whereas programmable switches carry out aggregation in the encrypted domain. Massive-scale simulations over realistic healthcare data sets demonstrate that EAH-FL preserves near-plaintext model accuracy (F1-score > 0.93), delivers packet delivery ratios > 0.95, and converges well for various client scales. The encryption expense is mostly incurred by the edge layer rather than resource-constrained wearables. Through the use of encryption, in- network acceleration, and smart routing, EAH-FL provides the first practical solution that achieves strong privacy, low latency, and scalability for real-time federated learning in healthcare in a single solution. These results validate its viability as a deployable and secure building block for next-generation digital health monitoring.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Wearable Electronic DevicesComputer SecurityHumansPrivacyInternet of ThingsComputer Communication NetworksAlgorithmsMachine LearningFederated Learning

Stichwörter der Autor:innen

edge computingfederated learninggraph neural networkshealthcare IoThomomorphic encryptionin-network computing

Autor:innen und Institutionen

  • Department of Computer Science, California State University Dominguez Hills, 1000 E. Victoria Street, Carson, CA 90747, USA.

ORCID-Profile: Rahul Kavati, Ali Jalooli

Zitieren

APA

Khan, H., Kavati, R., Pulkaram, S. S., & Jalooli, A. (2025). End-to-End Privacy-Aware Federated Learning for Wearable Health Devices via Encrypted Aggregation in Programmable Networks. Sensors, 25(22), 7023. https://doi.org/10.3390/s25227023

Vancouver

Khan H, Kavati R, Pulkaram SS, Jalooli A. End-to-End Privacy-Aware Federated Learning for Wearable Health Devices via Encrypted Aggregation in Programmable Networks. Sensors. 2025;25(22):7023. doi:10.3390/s25227023

BibTeX
@article{Khan2025,
  author = {Khan, Huzaif and Kavati, Rahul and Pulkaram, Sriven Srilakshmi and Jalooli, Ali},
  title = {End-to-End Privacy-Aware Federated Learning for Wearable Health Devices via Encrypted Aggregation in Programmable Networks},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {22},
  pages = {7023},
  doi = {10.3390/s25227023}
}
Kostenlos starten →