mlsanityData to 7 Oct 2026

CAT: Customized Adversarial Training for Improved Robustness

arXiv 2002.06789 ↗First posted 17 Feb 2020cs.LG stat.MLcited by 61

Not on the map. Why?

Abstract (arXiv)

Adversarial training has become one of the most effective methods for improving robustness of neural networks. However, it often suffers from poor generalization on both clean and perturbed data. In this paper, we propose a new algorithm, named Customized Adversarial Training (CAT), which adaptively customizes the perturbation level and the corresponding label for each training sample in adversarial training. We show that the proposed algorithm achieves better clean and robust accuracy than previous adversarial training methods through extensive experiments.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 12; 2023: 14; 2024: 16; 2025: 2; 2026: 2.

61 papers.

Sort:

By area:

  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  2. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 206
  3. 2021Exploring Memorization in Adversarial Trainingcited by 55
  4. 2023CFA: Class-wise Calibrated Fair Adversarial Trainingcited by 53
  5. 2021Adversarial Robustness with Semi-Infinite Constrained Learningcited by 39
  6. 2022Fast Adversarial Training with Adaptive Step Sizecited by 24
  7. 2024MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsificationcited by 20
  8. 2023Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothingcited by 18
  9. 2021SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluationcited by 16
  10. 2024MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifierscited by 16
  11. 2022Improving Robustness by Enhancing Weak Subnetscited by 12
  12. 2022Why adversarial training can hurt robust accuracycited by 12
38 more
  1. 2022Holistic Adversarial Robustness of Deep Learning Modelscited by 11
  2. 2021AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learningcited by 10
  3. 2021Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queriescited by 9
  4. 2021Guided Interpolation for Adversarial Trainingcited by 8
  5. 2021NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labelscited by 8
  6. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 8
  7. 2021Consistent Non-Parametric Methods for Maximizing Robustnesscited by 7
  8. 2021Domain Invariant Adversarial Learningcited by 7
  9. 2023Raising the Bar for Certified Adversarial Robustness with Diffusion Modelscited by 7
  10. 2021Adversarial Learning with Cost-Sensitive Classescited by 6
  11. 2023Provable Unrestricted Adversarial Training without Compromise with Generalizabilitycited by 6
  12. 2023Combining Adversaries with Anti-adversaries in Trainingcited by 6
  13. 2021Insta-RS: Instance-wise Randomized Smoothing for Improved Robustness and Accuracycited by 5
  14. 2023Improved Adversarial Training Through Adaptive Instance-wise Loss Smoothingcited by 5
  15. 2024Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledgecited by 5
  16. 2022Adaptive Adversarial Training to Improve Adversarial Robustness of DNNs for Medical Image Segmentation and Detectioncited by 4
  17. 2022A3T: Accuracy Aware Adversarial Trainingcited by 4
  18. 2023Splitting the Difference on Adversarial Trainingcited by 4
  19. 2024A Parametric Approach to Adversarial Augmentation for Cross-Domain Iris Presentation Attack Detectioncited by 4
  20. 2022Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of Perturbationscited by 3
  21. 2022Why is the video analytics accuracy fluctuating, and what can we do about it?cited by 3
  22. 2022Strength-Adaptive Adversarial Trainingcited by 3
  23. 2024Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustnesscited by 3
  24. 2024A Hybrid Training-time and Run-time Defense Against Adversarial Attacks in Modulation Classificationcited by 3
  25. 2024Solving Differential Equations with Constrained Learningcited by 3
  26. 2021Robust Training Using Natural Transformationcited by 2
  27. 2022Adversarial Fine-tune with Dynamically Regulated Adversarycited by 2
  28. 2024Specification Overfitting in Artificial Intelligencecited by 2
  29. 2024Explaining the role of Intrinsic Dimensionality in Adversarial Trainingcited by 2
  30. 2024New Paradigm of Adversarial Training: Releasing Accuracy-Robustness Trade-Off via Dummy Classcited by 2
  31. 2025Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Trainingcited by 2
  32. 2021Data Efficient Human Intention Prediction: Leveraging Neural Network Verification and Expert Guidancecited by 1
  33. 2021Calibrated Adversarial Trainingcited by 1
  34. 2024Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentationcited by 1
  35. 2024PUMA: margin-based data pruningcited by 1
  36. 2024Improving Adversarial Robustness via Feature Pattern Consistency Constraintcited by 1
  37. 2024Improving Clean Accuracy via a Tangent-Space Perspective on Adversarial Trainingcited by 1
  38. 2024Conflict-Aware Adversarial Trainingcited by 1

50 most cited of 61 All 61 (JSON)