EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SA-FLIDS: secure and authenticated federated learning-based intelligent network intrusion detection system for smart healthcare

Radjaa Bensaid, Nabila Labraoui, Ado Adamou Abba Ari iD, Hafida Saidi iD, Joel Herve Mboussam Emati, Leandros Maglaras iD

PeerJ Computer Science · 13.12.2024 · 10 · e2414

DOI: 10.7717/peerj-cs.2414 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 13.12.2024. Verfasst von Radjaa Bensaid und 5 weiteren Autor:innen. Beteiligte Einrichtung: STIC Lab, Abou Bekr Belkaid Tlemcen University, Tlemcen, Algeria. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Smart healthcare systems are gaining increased practicality and utility, driven by continuous advancements in artificial intelligence technologies, cloud and fog computing, and the Internet of Things (IoT). However, despite these transformative developments, challenges persist within IoT devices, encompassing computational constraints, storage limitations, and attack vulnerability. These attacks target sensitive health information, compromise data integrity, and pose obstacles to the overall resilience of the healthcare sector. To address these vulnerabilities, Network-based Intrusion Detection Systems (NIDSs) are crucial in fortifying smart healthcare networks and ensuring secure use of IoMT-based applications by mitigating security risks. Thus, this article proposes a novel Secure and Authenticated Federated Learning-based NIDS framework using Blockchain (SA-FLIDS) for fog-IoMT-enabled smart healthcare systems. Our research aims to improve data privacy and reduce communication costs. Furthermore, we also address weaknesses in decentralized learning systems, like Sybil and Model Poisoning attacks. We leverage the blockchain-based Self-Sovereign Identity (SSI) model to handle client authentication and secure communication. Additionally, we use the Trimmed Mean method to aggregate data. This helps reduce the effect of unusual or malicious inputs when creating the overall model. Our approach is evaluated on real IoT traffic datasets such as CICIoT2023 and EdgeIIoTset. It demonstrates exceptional robustness against adversarial attacks. These findings underscore the potential of our technique to improve the security of IoMT-based healthcare applications.

Schlagwörter

Stichwörter der Autor:innen

CybersecurityIntrusion detectionSmart healthcare

Autor:innen und Institutionen

  • STIC Lab, Abou Bekr Belkaid Tlemcen University, Tlemcen, Algeria.
  • LRI Lab, Abou Bekr Belkaid Tlemcen University, Tlemcen, Algeria.
  • LaRI Lab, University of Maroua, Cameroon, Cameroon.
  • Department of Mathematics and Computer Sciences, University of Dschang, Cameroon.
  • School of Computer Science, Edinburgh Napier University, Edinburgh, United Kingdom.

ORCID-Profile: Ado Adamou Abba Ari, Hafida Saidi, Leandros Maglaras

Zitieren

APA

Bensaid, R., Labraoui, N., Abba Ari, A. A., Saidi, H., Mboussam Emati, J. H., & Maglaras, L. (2024). SA-FLIDS: secure and authenticated federated learning-based intelligent network intrusion detection system for smart healthcare. PeerJ Computer Science, 10, e2414. https://doi.org/10.7717/peerj-cs.2414

Vancouver

Bensaid R, Labraoui N, Abba Ari AA, Saidi H, Mboussam Emati JH, Maglaras L. SA-FLIDS: secure and authenticated federated learning-based intelligent network intrusion detection system for smart healthcare. PeerJ Computer Science. 2024;10:e2414. doi:10.7717/peerj-cs.2414

BibTeX
@article{Bensaid2024,
  author = {Bensaid, Radjaa and Labraoui, Nabila and Abba Ari, Ado Adamou and Saidi, Hafida and Mboussam Emati, Joel Herve and Maglaras, Leandros},
  title = {SA-FLIDS: secure and authenticated federated learning-based intelligent network intrusion detection system for smart healthcare},
  journal = {PeerJ Computer Science},
  year = {2024},
  volume = {10},
  pages = {e2414},
  doi = {10.7717/peerj-cs.2414}
}
Kostenlos starten →