EUVIMEDEUVIMED entdecken
Crossref

Collaborative Multimodal Learning Over Integrated Aerial–Terrestrial Networks Under Adversarial Attacks

Shaba Shaon, Dinh C. Nguyen, Dusit Niyato, H. Vincent Poor

IEEE Transactions on Communications · 2026 · 74 · 8042-8058

DOI: 10.1109/tcomm.2026.3686736 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Communications, 2026. Verfasst von Shaba Shaon und 3 weiteren Autor:innen. Gefördert von: U.S. National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid growth of intelligent aerial-terrestrial applications, enabling collaborative multimodal learning (CML) across heterogeneous data sources, such as aerial images from unmanned aerial vehicles (UAVs) and time-series signals from ground edge devices (EDs), has become essential for achieving reliable intelligence beyond unimodal approaches. However, aerial-terrestrial CML systems face stringent latency requirements, limited energy and computation resources, and vulnerability to adversarial attacks, which are not jointly addressed in existing studies. This paper proposes a wireless aerial-terrestrial CML framework that integrates distributed UAVs and terrestrial EDs with modality-specific encoder training and multimodal fusion at a ground base station (BS). We formulate a latency minimization problem under energy, and security-aware constraints by jointly optimizing UAV trajectories and resource allocation, ED resource allocation, as well as resource allocation of the BS. The framework explicitly incorporates both passive eavesdropping and active interference attacks to ensure secure and robust aerial-terrestrial CML operation. To solve the resulting non-convex latency minimization problem, we develop a simple yet efficient iterative optimization algorithm to find a high-quality optimal solution based on successive convex approximation. Extensive simulation results with real-world datasets demonstrate that the proposed framework significantly outperforms existing training methods in terms of accuracy, loss, and convergence. Moreover, our joint optimization framework achieves up to 94.05% lower latency and stronger robustness against aerial adversaries compared with baseline schemes.

Förderung

  • U.S. National Science Foundation

Zitieren

APA

Shaon, S., Nguyen, D. C., Niyato, D., & Poor, H. V. (2026). Collaborative Multimodal Learning Over Integrated Aerial–Terrestrial Networks Under Adversarial Attacks. IEEE Transactions on Communications, 74, 8042-8058. https://doi.org/10.1109/tcomm.2026.3686736

Vancouver

Shaon S, Nguyen DC, Niyato D, Poor HV. Collaborative Multimodal Learning Over Integrated Aerial–Terrestrial Networks Under Adversarial Attacks. IEEE Transactions on Communications. 2026;74:8042-8058. doi:10.1109/tcomm.2026.3686736

BibTeX
@article{Shaon2026,
  author = {Shaon, Shaba and Nguyen, Dinh C. and Niyato, Dusit and Poor, H. Vincent},
  title = {Collaborative Multimodal Learning Over Integrated Aerial–Terrestrial Networks Under Adversarial Attacks},
  journal = {IEEE Transactions on Communications},
  year = {2026},
  volume = {74},
  pages = {8042--8058},
  doi = {10.1109/tcomm.2026.3686736}
}
Kostenlos starten →