mlsanityData to 13 Oct 2026

Robustness to Adversarial Perturbations in Learning from Incomplete Data

arXiv 1905.13021 ↗First posted 24 May 2019stat.ML cs.IT cs.LGcited by 49

Not on the map. Why?

Abstract (arXiv)

What is the role of unlabeled data in an inference problem, when the presumed underlying distribution is adversarially perturbed? To provide a concrete answer to this question, this paper unifies two major learning frameworks: Semi-Supervised Learning (SSL) and Distributionally Robust Learning (DRL). We develop a generalization theory for our framework based on a number of novel complexity measures, such as an adversarial extension of Rademacher complexity and its semi-supervised analogue. Moreover, our analysis is able to quantify the role of unlabeled data in the generalization under a more general condition compared to the existing theoretical works in SSL. Based on our framework, we also present a hybrid of DRL and EM algorithms that has a guaranteed convergence rate. When implemented with deep neural networks, our method shows a comparable performance to those of the state-of-the-art on a number of real-world benchmark datasets.

Key facts. Cited by 49 papers in the map (data through 13 Oct 2026). First posted on arXiv 24 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 17; 2022: 10; 2023: 8; 2024: 6; 2025: 6; 2026: 2.

49 papers.

Sort:

By area:

  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 278
  2. 2021Improving Robustness using Generated Datacited by 234
  3. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 208
  4. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 203
  5. 2021Data Augmentation Can Improve Robustnesscited by 193
  6. 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
  7. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  8. 2021Distributionally Robust Learningcited by 44
  9. 2021CausalAdv: Adversarial Robustness through the Lens of Causalitycited by 37
  10. 2022A Unified Wasserstein Distributional Robustness Framework for Adversarial Trainingcited by 36
  11. 2023Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustnesscited by 35
  12. 2021Assessing Fairness in the Presence of Missing Datacited by 24
37 more
  1. 2021Removing Undesirable Feature Contributions Using Out-of-Distribution Datacited by 23
  2. 2022Denoising Masked AutoEncoders Help Robust Classificationcited by 21
  3. 2022Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustnesscited by 20
  4. 2023Generalist: Decoupling Natural and Robust Generalizationcited by 14
  5. 2023Understanding and Improving Ensemble Adversarial Defensecited by 14
  6. 2022A Characterization of Semi-Supervised Adversarially-Robust PAC Learnabilitycited by 13
  7. 2022Global-Local Regularization Via Distributional Robustnesscited by 11
  8. 2021Understanding Generalization in Adversarial Training via the Bias-Variance Decompositioncited by 10
  9. 2021MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Mapscited by 9
  10. 2023It Is All About Data: A Survey on the Effects of Data on Adversarial Robustnesscited by 9
  11. 2021Guided Interpolation for Adversarial Trainingcited by 8
  12. 2021NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labelscited by 8
  13. 2024Robust Semi-Supervised Learning in Open Environmentscited by 8
  14. 2024Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Trainingcited by 6
  15. 2021Explaining Adversarial Vulnerability with a Data Sparsity Hypothesiscited by 4
  16. 2022Unlabeled Data Help: Minimax Analysis and Adversarial Robustnesscited by 4
  17. 2022Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attackscited by 4
  18. 2021Bridged Adversarial Trainingcited by 3
  19. 2022Why is the video analytics accuracy fluctuating, and what can we do about it?cited by 3
  20. 2023Out-Of-Domain Unlabeled Data Improves Generalizationcited by 3
  21. 2023Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Taskscited by 2
  22. 2024New Paradigm of Adversarial Training: Releasing Accuracy-Robustness Trade-Off via Dummy Classcited by 2
  23. 2025RideKE: Leveraging Low-Resource, User-Generated Twitter Content for Sentiment and Emotion Detection in Kenyan Code-Switched Datasetcited by 2
  24. 2021Improving Global Adversarial Robustness Generalization With Adversarially Trained GANcited by 1
  25. 2021Adversarial Heart Attack: Neural Networks Fooled to Segment Heart Symbols in Chest X-Ray Imagescited by 1
  26. 2022Two Heads are Better than One: Robust Learning Meets Multi-branch Modelscited by 1
  27. 2023Adversarial Training with Generated Data in High-Dimensional Regression: An Asymptotic Studycited by 1
  28. 2025A Flat Minima Perspective on Understanding Augmentations and Model Robustnesscited by 1
  29. 2025Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Trainingcited by 1
  30. 2024Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspectivecited by 0
  31. 2024Deep Learning with Data Privacy via Residual Perturbationcited by 0
  32. 2024NPAT Null-Space Projected Adversarial Training Towards Zero Deteriorationcited by 0
  33. 2025Efficient Semi-Supervised Adversarial Training via Latent Clustering-Based Data Reductioncited by 0
  34. 2025How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?cited by 0
  35. 2025Adversarial generalization of unfolding (model-based) networkscited by 0
  36. 2026Theoretical Analysis of Measure Consistency Regularization for Partially Observed Datacited by 0
  37. 2026Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Trainingcited by 0