Towards Collaborative and Cross-Environment UAV Classification: Federated Semantic Regularization

Fu, Xue ORCID: https://orcid.org/0000-0001-9518-4081, Wang, Yu ORCID: https://orcid.org/0000-0001-7763-4261, Lin, Yun ORCID: https://orcid.org/0000-0002-4002-1282, Ohtsuki, Tomoaki ORCID: https://orcid.org/0000-0003-3961-1426, Adebisi, Bamidele ORCID: https://orcid.org/0000-0001-9071-9120, Gui, Guan ORCID: https://orcid.org/0000-0003-3888-2881 and Sari, Hikmet ORCID: https://orcid.org/0000-0001-8114-6164 (2025) Towards Collaborative and Cross-Environment UAV Classification: Federated Semantic Regularization. IEEE Transactions on Information Forensics and Security, 20. pp. 1624-1635. ISSN 1556-6013

Preview

Accepted Version Available under License Creative Commons Attribution. Download (3MB) | Preview

Abstract

The rapid and widespread adoption of unmanned aerial vehicles (UAVs) poses significant threats to public safety and security in sensitive areas and subsequently underscores the urgent need for effective UAV surveillance solutions, where UAV classification emerges as a vital technology. Deep learning (DL) methods can autonomously extract implicit features from UAV signals and subsequently infer their types, provided that sufficient signal samples are available. Due to the high mobility of UAVs, it is challenging to ensure continuous monitoring between UAVs and the surveillance system to obtain sufficient samples. Moreover, DL models developed from sufficient but environment-specific datasets tend to be less generalized. This paper proposes a novel federated semantic regularization for learning an UAV classification model and further classifying UAVs across diverse environmental conditions. The approach enhances model generalization by regularizing semantic features during the local model training process on each participant. Subsequently, these local models are aggregated into a robust global model. Extensive testing across multiple environments demonstrates the superior classification performance of our approach compared to existing non-federated and federated approaches. The average classification accuracy of the proposed method in the three environments is 95.68%, which is improved by 13.39% compared to the non-federated methods and by 2.75% compared to the federated methods.