Secure Split Offloading and Trajectory Design for UAV-Assisted Multi-Exit Collaborative DNN Inference

Abstract

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.