mlsanityData to 7 Oct 2026

Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples

arXiv 2206.03353 ↗First posted 7 Jun 2022stat.ML cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we propose a new adversarial training algorithm that is theoretically well motivated and empirically superior to other existing algorithms. A novel feature of the proposed algorithm is to apply more regularization to data vulnerable to adversarial attacks than other existing regularization algorithms do. Theoretically, we show that our algorithm can be understood as an algorithm of minimizing the regularized empirical risk motivated from a newly derived upper bound of the robust risk. Numerical experiments illustrate that our proposed algorithm improves the generalization (accuracy on examples) and robustness (accuracy on adversarial attacks) simultaneously to achieve the state-of-the-art performance.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 38 of its 48 references that are in the map. First posted on arXiv 7 Jun 2022.

Builds on

38 of 48 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2017On Calibration of Modern Neural Networkscited by 4,860
  8. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  9. 2016Wide Residual Networkscited by 3,057
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  12. 2016Adversarial examples in the physical worldcited by 1,762
26 more
  1. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  2. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  3. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  4. 2019When Does Label Smoothing Help?cited by 985
  5. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  6. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  7. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  8. 2020Overfitting in adversarially robust deep learningcited by 504
  9. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  10. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
  11. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  12. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  13. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  14. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  15. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  16. 2021Data Augmentation Can Improve Robustnesscited by 193
  17. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 171
  18. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  19. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  20. 2016Towards the Science of Security and Privacy in Machine Learningcited by 89
  21. 2020An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Modelscited by 67
  22. 2018Adversarial Attacks Against Medical Deep Learning Systemscited by 61
  23. 2019Black-box Adversarial Attacks on Video Recognition Modelscited by 58
  24. 2019Fooling a Real Car with Adversarial Traffic Signscited by 29
  25. 2021Evaluating the Robustness of Geometry-Aware Instance-Reweighted Adversarial Trainingcited by 12
  26. 2022Sequential Bayesian Neural Subnetwork Ensemblescited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 5; 2025: 4.

11 papers.

  1. 2024ADBM: Adversarial diffusion bridge model for reliable adversarial purificationcited by 24
  2. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  3. 2024A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offscited by 5
  4. 2024FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Trainingcited by 5
  5. 2023Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillationcited by 3
  6. 2024Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Trainingcited by 2
  7. 2025TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justificationcited by 2
  8. 2025Robustness Feature Adapter for Efficient Adversarial Trainingcited by 2
  9. 2024Adversarial Training in Low-Label Regimes with Margin-Based Interpolationcited by 0
  10. 2025Sharpness-Aware Geometric Defense for Robust Out-Of-Distribution Detectioncited by 0
  11. 2025Improving Adversarial Robustness of Zero-Shot CLIP with Confidence-Aware Weightingcited by 0