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.
@article{arxiv.2512.10496,
title = {T-ADD: Enhancing DOA Estimation Robustness Against Adversarial Attacks},
author = {Shilian Zheng and Xiaoxiang Wu and Luxin Zhang and Keqiang Yue and Peihan Qi and Zhijin Zhao},
journal= {arXiv preprint arXiv:2512.10496},
year = {2025}
}