Jamming Identification with Differential Transformer for Low-Altitude Wireless Networks

TL;DR

This paper introduces a differential transformer framework with a randomized masking training strategy for robust wireless jamming identification in low-altitude drone networks, effectively resisting adversarial attacks.

Contribution

The paper proposes a novel differential transformer architecture combined with a randomized masking training method to enhance robustness against adversarial samples in wireless jamming detection.

Findings

Outperforms existing methods in adversarial robustness

Effective in distinguishing jamming signals in low-altitude networks

Demonstrates significant resilience to crafted adversarial samples

Abstract

Wireless jamming identification, which detects and classifies electromagnetic jamming from non-cooperative devices, is crucial for emerging low-altitude wireless networks consisting of many drone terminals that are highly susceptible to electromagnetic jamming. However, jamming identification schemes adopting deep learning (DL) are vulnerable to attacks involving carefully crafted adversarial samples, resulting in inevitable robustness degradation. To address this issue, we propose a differential transformer framework for wireless jamming identification. Firstly, we introduce a differential transformer network in order to distinguish jamming signals, which overcomes the attention noise when compared with its traditional counterpart by performing self-attention operations in a differential manner. Secondly, we propose a randomized masking training strategy to improve network robustness, which leverages the patch partitioning mechanism inherent to transformer architectures in order to create parallel feature extraction branches. Each branch operates on a distinct, randomly masked subset of patches, which fundamentally constrains the propagation of adversarial perturbations across the network. Additionally, the ensemble effect generated by fusing predictions from these diverse branches demonstrates superior resilience against adversarial attacks. Finally, we introduce a novel consistent training framework that significantly enhances adversarial robustness through dualbranch regularization. Simulation results demonstrate that our proposed methodology is superior to existing methods in boosting robustness to adversarial samples.