mlsanityData to 7 Oct 2026

Strength-Adaptive Adversarial Training

arXiv 2210.01288 ↗First posted 4 Oct 2022cs.LG cs.CRcited by 3

Not on the map. Why?

Abstract (arXiv)

Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness disparity between natural and robust accuracies, which deviates from robust network's desideratum. Secondly, the attack strength of adversarial training data constrained by the pre-specified perturbation budget fails to upgrade as the growth of network robustness, which leads to robust overfitting and further degrades the adversarial robustness. To overcome these limitations, we propose Strength-Adaptive Adversarial Training (SAAT). Specifically, the adversary employs an adversarial loss constraint to generate adversarial training data. Under this constraint, the perturbation budget will be adaptively adjusted according to the training state of adversarial data, which can effectively avoid robust overfitting. Besides, SAAT explicitly constrains the attack strength of training data through the adversarial loss, which manipulates model capacity scheduling during training, and thereby can flexibly control the degree of robustness disparity and adjust the tradeoff between natural accuracy and robustness. Extensive experiments show that our proposal boosts the robustness of adversarial training.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 43 of its 68 references that are in the map. First posted on arXiv 4 Oct 2022.

Builds on

43 of 68 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2016Wide Residual Networkscited by 3,057
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  11. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  12. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
31 more
  1. 2018Robustness May Be at Odds with Accuracycited by 873
  2. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  3. 2020Overfitting in adversarially robust deep learningcited by 504
  4. 2019On Evaluating Adversarial Robustnesscited by 442
  5. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  6. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  7. 2018Adversarially Robust Generalization Requires More Datacited by 318
  8. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  9. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  10. 2021Data Augmentation Can Improve Robustnesscited by 193
  11. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
  12. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 171
  13. 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
  14. 2020Understanding and Mitigating the Tradeoff Between Robustness and Accuracycited by 148
  15. 2018Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Modelscited by 135
  16. 2021On the Convergence and Robustness of Adversarial Trainingcited by 127
  17. 2018Curriculum Adversarial Trainingcited by 89
  18. 2021Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Bettercited by 77
  19. 2019Adversarially Robust Generalization Just Requires More Unlabeled Datacited by 75
  20. 2020CAT: Customized Adversarial Training for Improved Robustnesscited by 61
  21. 2020On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Themcited by 59
  22. 2021Probabilistic Margins for Instance Reweighting in Adversarial Trainingcited by 57
  23. 2019Instance adaptive adversarial training: Improved accuracy tradeoffs in neural netscited by 55
  24. 2021Exploring Memorization in Adversarial Trainingcited by 55
  25. 2022Understanding Robust Overfitting of Adversarial Training and Beyondcited by 50
  26. 2019Adversarial Robustness May Be at Odds With Simplicitycited by 39
  27. 2021Towards Defending against Adversarial Examples via Attack-Invariant Featurescited by 25
  28. 2022Robust Weight Perturbation for Adversarial Trainingcited by 25
  29. 2017Residual Convolutional CTC Networks for Automatic Speech Recognitioncited by 21
  30. 2021Removing Adversarial Noise in Class Activation Feature Spacecited by 18
  31. 2021On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Trainingcited by 11

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 2.

3 papers.

  1. 2023Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspectivecited by 18
  2. 2025AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editingcited by 9
  3. 2025Ensemble Distribution Distillation for Self-Supervised Human Activity Recognitioncited by 0