Federated Learning for Intrusion Detection in UAV Networks
Turkish Journal of Mathematics and Computer Science · 30.06.2026 · 18 (2) · 481-503
DOI: 10.47000/tjmcs.1828534 ↗Kurz gefasst
Fachartikel in der Zeitschrift Turkish Journal of Mathematics and Computer Science, online erschienen am 30.06.2026. Verfasst von Deniz Berke Özsoy und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 23 Literaturangaben.
Abstract (Originalsprache)
UAV swarms operate under bandwidth constraints, intermittent connectivity, and privacy requirements that make fully centralized intrusion detection difficult. Using the UAVIDS--2025 benchmark, we construct a deployment-oriented federated intrusion detection setting by partitioning flows by source address into $K{=}176$ realistic, strongly non-IID clients, where each client approximates the traffic observed by an individual UAV. We train a compact multilayer perceptron ($22\!\rightarrow\!64\!\rightarrow\!32\!\rightarrow\!5$) across three federated optimizers (FedAvg, FedProx, and SCAFFOLD) and employ a leakage-safe feature pipeline that removes identifier and scenario fields while retaining mechanism-based traffic and QoS descriptors. Under a matched training and communication budget, FedAvg achieves $93\%$ accuracy, $93\%$ macro-F1, and AUROC $0.99$ on a held-out global test set, within roughly three percentage points of strong centralized baselines (XGBoost and LightGBM at $96\%$) that train on fully aggregated traffic. FedProx trades peak performance for more stable convergence ($86\%$ accuracy, $84\%$ macro-F1), whereas SCAFFOLD reduces communication but shows more pronounced classwise weaknesses ($82\%$ accuracy, $79\%$ macro-F1) under our current tuning. We report the communication footprint in MB per round and cumulatively, and we repeat the same held-out evaluation protocol on a second intrusion dataset (T-ITS) to assess transfer of optimizer trends. Overall, the results indicate that leakage-safe federated learning can keep raw UAV traffic local while recovering most of the detection quality of strong centralized models, clarifying accuracy--communication trade-offs for privacy-preserving IDS deployment in UAV swarms.
Zitieren
APA
Özsoy, D. B., Özcan, A., & Al-Hubaishi, M. (2026). Federated Learning for Intrusion Detection in UAV Networks. Turkish Journal of Mathematics and Computer Science, 18(2), 481-503. https://doi.org/10.47000/tjmcs.1828534
Vancouver
Özsoy DB, Özcan A, Al-Hubaishi M. Federated Learning for Intrusion Detection in UAV Networks. Turkish Journal of Mathematics and Computer Science. 2026;18(2):481-503. doi:10.47000/tjmcs.1828534
BibTeX
@article{zsoy2026,
author = {Özsoy, Deniz Berke and Özcan, Atakan and Al-Hubaishi, Mohammed},
title = {Federated Learning for Intrusion Detection in UAV Networks},
journal = {Turkish Journal of Mathematics and Computer Science},
year = {2026},
volume = {18},
number = {2},
pages = {481--503},
doi = {10.47000/tjmcs.1828534}
}
EUVIMED