Joint Optimization of Model Partitioning and Resource Allocation for Anti-Jamming Collaborative Inference Systems
This addresses security and efficiency issues for resource-constrained devices in edge computing, but it is incremental as it builds on existing collaborative inference paradigms.
The paper tackles the problem of jamming attacks degrading performance in device-edge collaborative DNN inference by jointly optimizing model partitioning, resource allocation, and transmit power to maximize a revenue metric of delay and accuracy, with simulations showing it outperforms baselines in terms of this metric.
With the increasing computational demands of deep neural network (DNN) inference on resource-constrained devices, DNN partitioning-based device-edge collaborative inference has emerged as a promising paradigm. However, the transmission of intermediate feature data is vulnerable to malicious jamming, which significantly degrades the overall inference performance. To counter this threat, this letter focuses on an anti-jamming collaborative inference system in the presence of a malicious jammer. In this system, a DNN model is partitioned into two distinct segments, which are executed by wireless devices and edge servers, respectively. We first analyze the effects of jamming and DNN partitioning on inference accuracy via data regression. Based on this, our objective is to maximize the system's revenue of delay and accuracy (RDA) under inference accuracy and computing resource constraints by jointly optimizing computation resource allocation, devices' transmit power, and DNN partitioning. To address the mixed-integer nonlinear programming problem, we propose an efficient alternating optimization-based algorithm, which decomposes the problem into three subproblems that are solved via Karush-Kuhn-Tucker conditions, convex optimization methods, and a quantum genetic algorithm, respectively. Extensive simulations demonstrate that our proposed scheme outperforms baselines in terms of RDA.