mlsanityData to 7 Oct 2026

Curriculum Adversarial Training

arXiv 1805.04807 ↗First posted 13 May 2018cs.LG cs.CR stat.MLcited by 89

Not on the map. Why?

Abstract (arXiv)

Recently, deep learning has been applied to many security-sensitive applications, such as facial authentication. The existence of adversarial examples hinders such applications. The state-of-the-art result on defense shows that adversarial training can be applied to train a robust model on MNIST against adversarial examples; but it fails to achieve a high empirical worst-case accuracy on a more complex task, such as CIFAR-10 and SVHN. In our work, we propose curriculum adversarial training (CAT) to resolve this issue. The basic idea is to develop a curriculum of adversarial examples generated by attacks with a wide range of strengths. With two techniques to mitigate the forgetting and the generalization issues, we demonstrate that CAT can improve the prior art's empirical worst-case accuracy by a large margin of 25% on CIFAR-10 and 35% on SVHN. At the same, the model's performance on non-adversarial inputs is comparable to the state-of-the-art models.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 22; 2023: 16; 2024: 12; 2025: 11; 2026: 3.

89 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. 2024Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Modelscited by 164
  4. 2021On the Convergence and Robustness of Adversarial Trainingcited by 127
  5. 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 94
  6. 2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
  7. 2021Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Trainingcited by 58
  8. 2021Reliable Adversarial Distillation with Unreliable Teacherscited by 55
  9. 2023CFA: Class-wise Calibrated Fair Adversarial Trainingcited by 53
  10. 2022Understanding Robust Overfitting of Adversarial Training and Beyondcited by 50
  11. 2021Accelerating Deep Learning with Dynamic Data Pruningcited by 43
  12. 2022Efficient and Effective Augmentation Strategy for Adversarial Trainingcited by 43
38 more
  1. 2023An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferabilitycited by 42
  2. 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
  3. 2021Robust Physical-World Attacks on Face Recognitioncited by 26
  4. 2021Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Informationcited by 25
  5. 2021Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attackscited by 24
  6. 2021CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selectioncited by 21
  7. 2024MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsificationcited by 20
  8. 2021Understanding the Interaction of Adversarial Training with Noisy Labelscited by 19
  9. 2023Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspectivecited by 18
  10. 2023Feature Separation and Recalibration for Adversarial Robustnesscited by 16
  11. 2022Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculumcited by 15
  12. 2021Two Coupled Rejection Metrics Can Tell Adversarial Examples Apartcited by 14
  13. 2021Towards Robust General Medical Image Segmentationcited by 14
  14. 2023Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averagingcited by 14
  15. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  16. 2021Neural Architecture Dilation for Adversarial Robustnesscited by 13
  17. 2023Less is More: Data Pruning for Faster Adversarial Trainingcited by 13
  18. 2021Learning Diverse-Structured Networks for Adversarial Robustnesscited by 12
  19. 2022Improving Robustness by Enhancing Weak Subnetscited by 12
  20. 2022RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Modelcited by 11
  21. 2022Analysis and Extensions of Adversarial Training for Video Classificationcited by 11
  22. 2022Enhancing Adversarial Robustness for Deep Metric Learningcited by 10
  23. 2021Guided Interpolation for Adversarial Trainingcited by 8
  24. 2021NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labelscited by 8
  25. 2021Detecting Localized Adversarial Examples: A Generic Approach using Critical Region Analysiscited by 7
  26. 2021Domain Invariant Adversarial Learningcited by 7
  27. 2021Style Curriculum Learning for Robust Medical Image Segmentationcited by 6
  28. 2021Push Stricter to Decide Better: A Class-Conditional Feature Adaptive Framework for Improving Adversarial Robustnesscited by 6
  29. 2023Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoffcited by 6
  30. 2024Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Trainingcited by 6
  31. 2024Adversarial Training: A Surveycited by 6
  32. 2025INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomycited by 5
  33. 2021Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approachcited by 4
  34. 2022Adaptive Adversarial Training to Improve Adversarial Robustness of DNNs for Medical Image Segmentation and Detectioncited by 4
  35. 2022Improving Out-of-Distribution Detection via Epistemic Uncertainty Adversarial Trainingcited by 4
  36. 2022Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attackscited by 4
  37. 2023Splitting the Difference on Adversarial Trainingcited by 4
  38. 2024The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspectivecited by 4

50 most cited of 89 All 89 (JSON)