Secure Split Offloading and Trajectory Design for UAV-Assisted Multi-Exit Collaborative DNN Inference
IEEE Transactions on Mobile Computing · 2026-10 · 25 (10) · 18924-18939
DOI: 10.1109/tmc.2026.3708394 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-10. Verfasst von Mengru Wu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Zhejiang Provincial Natural Science Foundation of China.
Abstract (Originalsprache)
Collaborative inference (CI) has emerged as a promising paradigm in mobile edge computing, where deep neural network (DNN) models are split and collaboratively processed by wireless devices and edge servers to reduce communication overhead and improve inference efficiency. Unmanned aerial vehicles (UAVs) with agile mobility present significant potential as edge servers in such systems. However, the limited computation resources of UAV servers and the inherent security vulnerabilities of ground-to-air channels pose challenges to UAV-assisted CI. To address these issues, this paper proposes a novel UAV-assisted CI framework via multi-exit DNNs and cooperative jamming. Specifically, this framework integrates an early-exit (EE) mechanism to alleviate computational burdens and employs a cooperative UAV jammer to transmit jamming signals to ensure secure split offloading. Our objective is to minimize total energy consumption while maximizing inference accuracy, subject to inference delay requirements and secure offloading rate constraints by jointly optimizing dual-UAV trajectories, EE selection, DNN partitioning, and computation resource allocation. To solve the formulated mixed-integer nonlinear programming problem, we first derive a closed-form solution for computation resource allocation and reformulate the optimization problem accordingly. We then develop an efficient alternating optimization algorithm that employs the successive convex approximation method for UAVs’ trajectory design and a discrete whale optimization algorithm for EE selection and DNN partitioning. Extensive simulation results demonstrate that the proposed scheme outperforms baselines.
Förderung
- National Natural Science Foundation of China
- Zhejiang Provincial Natural Science Foundation of China
Zitieren
APA
Wu, M., Wu, H., Lu, W., Ning, Z., Guo, L., & Jamalipour, A. (2026). Secure Split Offloading and Trajectory Design for UAV-Assisted Multi-Exit Collaborative DNN Inference. IEEE Transactions on Mobile Computing, 25(10), 18924-18939. https://doi.org/10.1109/tmc.2026.3708394
Vancouver
Wu M, Wu H, Lu W, Ning Z, Guo L, Jamalipour A. Secure Split Offloading and Trajectory Design for UAV-Assisted Multi-Exit Collaborative DNN Inference. IEEE Transactions on Mobile Computing. 2026;25(10):18924-18939. doi:10.1109/tmc.2026.3708394
BibTeX
@article{Wu2026,
author = {Wu, Mengru and Wu, Haonan and Lu, Weidang and Ning, Zhaolong and Guo, Lei and Jamalipour, Abbas},
title = {Secure Split Offloading and Trajectory Design for UAV-Assisted Multi-Exit Collaborative DNN Inference},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {10},
pages = {18924--18939},
doi = {10.1109/tmc.2026.3708394}
}
EUVIMED