{"ID":3004664,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-05T11:43:53.432517148Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.03925","arxiv_id":"2606.03925","title":"Adaptive Causal Alignment for High-Confidence Adversarial Training","abstract":"Inverse adversarial training leverages high-confidence predictions to stabilize robust learning, yet we uncover a critical paradox: high confidence often stems from overfitting to non-causal background correlations rather than intrinsic object semantics. Our investigation reveals that visual context functions as a dual-natured signal, serving as either a necessary supportive prior or a spurious confounder. This insight renders existing blind suppression strategies flawed, as they inevitably lead to severe Feature Loss. To resolve this, we propose High-Confidence Causally Aligned Training (HICAT), a unified framework that establishes a Semantic Equilibrium. Operating on a ``Measure-Debias-Align'' pipeline, HICAT integrates a Learnable Background-Bias Estimator (LBBE) to adaptively diagnose context utility. Guided by this diagnosis, an Adaptive Debiasing mechanism performs surgical logit rectification, complemented by a geometrically grounded Foreground Logit Orthogonal Enhancement (FLOE) loss to enforce rigorous feature disentanglement. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K demonstrate that HICAT consistently improves over matched baselines across diverse architectures (CNNs and ViTs) while significantly reducing the robust generalization gap.","short_abstract":"Inverse adversarial training leverages high-confidence predictions to stabilize robust learning, yet we uncover a critical paradox: high confidence often stems from overfitting to non-causal background correlations rather than intrinsic object semantics. Our investigation reveals that visual context functions as a dual...","url_abs":"https://arxiv.org/abs/2606.03925","url_pdf":"https://arxiv.org/pdf/2606.03925v1","authors":"[\"Zhiming Luo\",\"Kejia Zhang\",\"Yingxin Lai\",\"Junwei Wu\",\"Juanjuan Weng\",\"Shaozi Li\"]","published":"2026-06-02T17:14:54Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false}