mlsanityData to 14 Oct 2026

Narrowing Class-Wise Robustness Gaps in Adversarial Training

arXiv 2503.16179 ↗First posted 20 Mar 2025cs.CV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Efforts to address declining accuracy as a result of data shifts often involve various data-augmentation strategies. Adversarial training is one such method, designed to improve robustness to worst-case distribution shifts caused by adversarial examples. While this method can improve robustness, it may also hinder generalization to clean examples and exacerbate performance imbalances across different classes. This paper explores the impact of adversarial training on both overall and class-specific performance, as well as its spill-over effects. We observe that enhanced labeling during training boosts adversarial robustness by 53.50% and mitigates class imbalances by 5.73%, leading to improved accuracy in both clean and adversarial settings compared to standard adversarial training.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 27 references that are in the map. First posted on arXiv 20 Mar 2025.

Builds on

24 of 27 references.

References · 24

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  8. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  9. 2016Adversarial Machine Learning at Scalecited by 936
  10. 2018Robustness May Be at Odds with Accuracycited by 880
  11. 2019On Evaluating Adversarial Robustnesscited by 447
  12. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
12 more
  1. 2020Are we done with ImageNet?cited by 333
  2. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 261
  3. 2017The Space of Transferable Adversarial Examplescited by 158
  4. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 97
  5. 2024DiffuseMix: Label-Preserving Data Augmentation with Diffusion Modelscited by 78
  6. 2022The Effects of Regularization and Data Augmentation are Class Dependentcited by 67
  7. 2020Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracycited by 45
  8. 2022ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotationscited by 44
  9. 2022How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularizationcited by 40
  10. 2019A Research Agenda: Dynamic Models to Defend Against Correlated Attackscited by 18
  11. 2023Understanding the Detrimental Class-level Effects of Data Augmentationcited by 13
  12. 2024Label Augmentation for Neural Networks Robustnesscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026GF-Score: Certified Class-Conditional Robustness Evaluation with Fairness Guaranteescited by 0