{"ID":2823324,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00968","arxiv_id":"2601.00968","title":"Explainability-Guided Defense: Attribution-Aware Model Refinement Against Adversarial Data Attacks","abstract":"The growing reliance on deep learning models in safety-critical domains such as healthcare and autonomous navigation underscores the need for defenses that are both robust to adversarial perturbations and transparent in their decision-making. In this paper, we identify a connection between interpretability and robustness that can be directly leveraged during training. Specifically, we observe that spurious, unstable, or semantically irrelevant features identified through Local Interpretable Model-Agnostic Explanations (LIME) contribute disproportionately to adversarial vulnerability. Building on this insight, we introduce an attribution-guided refinement framework that transforms LIME from a passive diagnostic into an active training signal. Our method systematically suppresses spurious features using feature masking, sensitivity-aware regularization, and adversarial augmentation in a closed-loop refinement pipeline. This approach does not require additional datasets or model architectures and integrates seamlessly into standard adversarial training. Theoretically, we derive an attribution-aware lower bound on adversarial distortion that formalizes the link between explanation alignment and robustness. Empirical evaluations on CIFAR-10, CIFAR-10-C, and CIFAR-100 demonstrate substantial improvements in adversarial robustness and out-of-distribution generalization.","short_abstract":"The growing reliance on deep learning models in safety-critical domains such as healthcare and autonomous navigation underscores the need for defenses that are both robust to adversarial perturbations and transparent in their decision-making. In this paper, we identify a connection between interpretability and robustne...","url_abs":"https://arxiv.org/abs/2601.00968","url_pdf":"https://arxiv.org/pdf/2601.00968v1","authors":"[\"Longwei Wang\",\"Mohammad Navid Nayyem\",\"Abdullah Al Rakin\",\"KC Santosh\",\"Chaowei Zhang\",\"Yang Zhou\"]","published":"2026-01-02T19:36:03Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}