T-ADD: Enhancing DOA Estimation Robustness Against Adversarial Attacks

TL;DR

This paper introduces T-ADD, a transformer-based method that enhances the robustness of DOA estimation models against adversarial attacks by jointly reconstructing signals and employing a specialized loss function.

Contribution

The paper presents a novel transformer-based adversarial defense approach for DOA estimation, combining joint reconstruction with a tailored loss to improve robustness.

Findings

T-ADD significantly reduces the impact of adversarial attacks.

It outperforms three state-of-the-art defense methods.

Experimental results show improved robustness and accuracy.

Abstract

Deep learning has achieved remarkable success in direction-of-arrival (DOA) estimation. However, recent studies have shown that adversarial perturbations can severely compromise the performance of such models. To address this vulnerability, we propose Transformer-based Adversarial Defense for DOA estimation (T-ADD), a transformer-based defense method designed to counter adversarial attacks. To achieve a balance between robustness and estimation accuracy, we formulate the adversarial defense as a joint reconstruction task and introduce a tailored joint loss function. Experimental results demonstrate that, compared with three state-of-the-art adversarial defense methods, the proposed T-ADD significantly mitigates the adverse effects of widely used adversarial attacks, leading to notable improvements in the adversarial robustness of the DOA model.