CGRm 解决了长尾对抗训练中类别不平衡和对抗放大双重问题，用混淆几何图精准定位关键边界，实验效果不错，值得做对抗训练的人看看。
CGRm 是一种用于长尾对抗训练的插件式框架，利用有向鲁棒误差作为训练信号。它通过周期性鲁棒评估推导源类损失权重、类级鲁棒系数和有向混淆几何图。该方法将反馈加权鲁棒优化与图引导的边界校正相结合，提升脆弱类别的鲁棒性。在长尾基准上的实验显示，CGRm 相比现有方法取得一致的鲁棒性能提升，消融实验验证了各组件贡献。
Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training
Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes, and the adversarial inner maximization may further amplify this bias. Existing methods mitigate this issue by correcting class priors or adapting class wise robust supervision, yet they treat each class in isolation and fail to identify which boundaries drive long tailed collapse. We propose a Confusion Geometry Rebalancing method (CGRm) for long tail adversarial training, a plug in framework that leverages directed robust errors as training signals. CGRm leverages periodic robust evaluations to derive source class loss weights, class wise robust coefficients, and a directed confusion geometry graph. The method then couples feedback weighted robust optimization with graph guided margin correction, thereby boosting the robustness of vulnerable classes and sharpening the critical boundaries that drive long tailed performance degradation. Experiments on long tailed benchmarks show that CGRm achieves consistent robust performance gains over existing methods, with ablations validating the contribution of each component. We provide the code in the supplement.