{"ID":2830210,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.10496","arxiv_id":"2512.10496","title":"T-ADD: Enhancing DOA Estimation Robustness Against Adversarial Attacks","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.","short_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...","url_abs":"https://arxiv.org/abs/2512.10496","url_pdf":"https://arxiv.org/pdf/2512.10496v1","authors":"[\"Shilian Zheng\",\"Xiaoxiang Wu\",\"Luxin Zhang\",\"Keqiang Yue\",\"Peihan Qi\",\"Zhijin Zhao\"]","published":"2025-12-11T10:17:52Z","proceeding":"eess.SP","tasks":"[\"eess.SP\"]","methods":"[\"Transformer\"]","has_code":false}