EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DBST-FL: Dynamic Behavioural and Semantic Trust for Robust Federated Learning in Industrial IoT

Ammar Alazab iD, Abin Kumbalapalliyil Tom iD, Tony Jan iD, Md Whaiduzzaman iD, Thien Nguyen iD, Ansam Khraisat iD, Ali Almazrouei iD

Sensors · 24.07.2026 · 26 (15) · 4712

DOI: 10.3390/s26154712 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.07.2026. Verfasst von Ammar Alazab und 6 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Artificial Intelligence Research and Optimization (AIRO), Torrens University Australia (TUA), 46-52 Mountain Street, Ultimo, NSW 2007, Aus…. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) has emerged as an effective paradigm for collaborative model training in Industrial Internet of Things (IIoT) environments by enabling distributed devices to learn shared models without exchanging raw data. However, existing FL defence mechanisms predominantly rely on either behavioural analysis of client updates or semantic validation of model performance, limiting their ability to detect sophisticated poisoning and stealthy backdoor attacks that evade single-dimensional trust assessment. This paper proposes DBST-FL, a dynamic behavioural and semantic trust framework for robust federated learning in the Industrial IoT. The proposed framework evaluates each client through two complementary trust dimensions: a behavioural trust layer that measures gradient alignment, historical consistency, and collective deviation and a semantic trust layer that assesses benign utility and template-free semantic stress validation using server-side data. The two trust scores are integrated through a non-compensatory multiplicative trust fusion mechanism, ensuring that weaknesses in one trust dimension cannot be masked by strengths in the other. The resulting trust score guides a trust-aware aggregation strategy that reduces the influence of malicious participants while preserving the contributions of reliable clients. Extensive experiments are conducted on the Edge-IIoTset and UNSW-NB15 datasets using ANN, 1D-CNN, and LSTM models under multiple poisoning and backdoor attack scenarios. The proposed framework achieves overall classification performance competitive with the strongest robust aggregation baselines while consistently delivering stronger resilience against adversarial attacks and lower backdoor attack success rates than representative trust-based and Byzantine-robust aggregation methods, all while maintaining linear per-round computational complexity suitable for large-scale IIoT deployments. The results demonstrate that integrating behavioural and semantic trust within a unified aggregation framework provides an effective and scalable defence against advanced adversarial threats in federated learning.

Schlagwörter

Stichwörter der Autor:innen

IIoT securityIndustrial Internet of Thingsadversarial robustnessbackdoor detectionbehavioural trustdynamic behavioural and semantic trustfederated learningmultiplicative trust fusionpoisoning attack mitigationsemantic trust validation

Autor:innen und Institutionen

  • Centre for Artificial Intelligence Research and Optimization (AIRO), Torrens University Australia (TUA), 46-52 Mountain Street, Ultimo, NSW 2007, Australia.
  • School of Information Technology, Deakin University, Melbourne Burwood Campus, Burwood, VIC 3125, Australia.
  • CyberNex, Somerton, VIC 3062, Australia.

ORCID-Profile: Ammar Alazab, Abin Kumbalapalliyil Tom, Tony Jan, Md Whaiduzzaman, Thien Nguyen, Ansam Khraisat, Ali Almazrouei

Zitieren

APA

Alazab, A., Tom, A. K., Jan, T., Whaiduzzaman, M., Nguyen, T., Khraisat, A., & Almazrouei, A. (2026). DBST-FL: Dynamic Behavioural and Semantic Trust for Robust Federated Learning in Industrial IoT. Sensors, 26(15), 4712. https://doi.org/10.3390/s26154712

Vancouver

Alazab A, Tom AK, Jan T, Whaiduzzaman M, Nguyen T, Khraisat A, et al. DBST-FL: Dynamic Behavioural and Semantic Trust for Robust Federated Learning in Industrial IoT. Sensors. 2026;26(15):4712. doi:10.3390/s26154712

BibTeX
@article{Alazab2026,
  author = {Alazab, Ammar and Tom, Abin Kumbalapalliyil and Jan, Tony and Whaiduzzaman, Md and Nguyen, Thien and Khraisat, Ansam and Almazrouei, Ali},
  title = {DBST-FL: Dynamic Behavioural and Semantic Trust for Robust Federated Learning in Industrial IoT},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {15},
  pages = {4712},
  doi = {10.3390/s26154712}
}
Kostenlos starten →