mlsanityData to 7 Oct 2026

Guided Interpolation for Adversarial Training

arXiv 2102.07327 ↗First posted 15 Feb 2021cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

To enhance adversarial robustness, adversarial training learns deep neural networks on the adversarial variants generated by their natural data. However, as the training progresses, the training data becomes less and less attackable, undermining the robustness enhancement. A straightforward remedy is to incorporate more training data, but sometimes incurring an unaffordable cost. In this paper, to mitigate this issue, we propose the guided interpolation framework (GIF): in each epoch, the GIF employs the previous epoch's meta information to guide the data's interpolation. Compared with the vanilla mixup, the GIF can provide a higher ratio of attackable data, which is beneficial to the robustness enhancement; it meanwhile mitigates the model's linear behavior between classes, where the linear behavior is favorable to generalization but not to the robustness. As a result, the GIF encourages the model to predict invariantly in the cluster of each class. Experiments demonstrate that the GIF can indeed enhance adversarial robustness on various adversarial training methods and various datasets.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 15 Feb 2021.

Builds on

35 of 51 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2016Wide Residual Networkscited by 3,057
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  11. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  12. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
23 more
  1. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  2. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  3. 2020Overfitting in adversarially robust deep learningcited by 504
  4. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  5. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  6. 2018Adversarially Robust Generalization Requires More Datacited by 318
  7. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  8. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  9. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  10. 2020Bag of Tricks for Adversarial Trainingcited by 199
  11. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  12. 2020How Does Mixup Help With Robustness and Generalization?cited by 193
  13. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 171
  14. 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
  15. 2021Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversitycited by 127
  16. 2016Towards the Science of Security and Privacy in Machine Learningcited by 89
  17. 2018Curriculum Adversarial Trainingcited by 89
  18. 2020CAT: Customized Adversarial Training for Improved Robustnesscited by 61
  19. 2019Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attackscited by 54
  20. 2019Robustness to Adversarial Perturbations in Learning from Incomplete Datacited by 49
  21. 2019Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracycited by 49
  22. 2020Single-step Adversarial training with Dropout Schedulingcited by 40
  23. 2020Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Trainingcited by 10

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 1; 2024: 2.

8 papers.

  1. 2022Understanding Robust Overfitting of Adversarial Training and Beyondcited by 50
  2. 2022Sparsity Winning Twice: Better Robust Generalization from More Efficient Trainingcited by 41
  3. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  4. 2022Robust Weight Perturbation for Adversarial Trainingcited by 25
  5. 2023Certified Robust Neural Networks: Generalization and Corruption Resistancecited by 11
  6. 2021MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Mapscited by 9
  7. 2024Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Trainingcited by 6
  8. 2024The Effectiveness of Random Forgetting for Robust Generalizationcited by 2