# Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training

arXiv: https://arxiv.org/abs/2608.09688 · HTML: https://mlsanity.com/paper/2608.09688/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [CFA: Class-wise Calibrated Fair Adversarial Training](https://mlsanity.com/paper/2303.14460/) (2023)
- [Adversarial Robustness under Long-Tailed Distribution](https://mlsanity.com/paper/2104.02703/) (2021)
- [Probabilistic Contrastive Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2403.06726/) (2024)
- [A Unified Wasserstein Distributional Robustness Framework for Adversarial Training](https://mlsanity.com/paper/2202.13437/) (2022)
- [Improving Fast Adversarial Training with Prior-Guided Knowledge](https://mlsanity.com/paper/2304.00202/) (2023)
- [Fast Adversarial Training with Smooth Convergence](https://mlsanity.com/paper/2308.12857/) (2023)
- [Revisiting Adversarial Training under Long-Tailed Distributions](https://mlsanity.com/paper/2403.10073/) (2024)
- [DAFA: Distance-Aware Fair Adversarial Training](https://mlsanity.com/paper/2401.12532/) (2024)
- [TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions](https://mlsanity.com/paper/2503.01924/) (2025)
- [Mitigating Error Amplification in Fast Adversarial Training](https://mlsanity.com/paper/2604.24332/) (2026)
- [Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation](https://mlsanity.com/paper/2605.13395/) (2026)

## Abstract (arXiv)

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.