mlsanityData to 14 Oct 2026

Squeeze Training for Adversarial Robustness

arXiv 2205.11156 ↗First posted 23 May 2022cs.LG cs.CR cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community. The problem is related to non-flatness and non-smoothness of normally obtained loss landscapes. Training augmented with adversarial examples (a.k.a., adversarial training) is considered as an effective remedy. In this paper, we highlight that some collaborative examples, nearly perceptually indistinguishable from both adversarial and benign examples yet show extremely lower prediction loss, can be utilized to enhance adversarial training. A novel method is therefore proposed to achieve new state-of-the-arts in adversarial robustness. Code: https://github.com/qizhangli/ST-AT.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 45 of its 54 references that are in the map. First posted on arXiv 23 May 2022.

Builds on

45 of 54 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2016Wide Residual Networkscited by 3,070
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  8. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  11. 2017Visualizing the Loss Landscape of Neural Netscited by 1,130
  12. 2016Adversarial Machine Learning at Scalecited by 936
33 more
  1. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  2. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  3. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  4. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  5. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  6. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  7. 2020Overfitting in adversarially robust deep learningcited by 506
  8. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
  9. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
  10. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  11. 2019Adversarial Examples Improve Image Recognitioncited by 286
  12. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 278
  13. 2021Improving Robustness using Generated Datacited by 234
  14. 2018Adversarial Logit Pairingcited by 224
  15. 2021Vision Transformers are Robust Learnerscited by 207
  16. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 204
  17. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  18. 2021Are Transformers More Robust Than CNNs?cited by 187
  19. 2018Robustness via curvature regularization, and vice versacited by 175
  20. 2021Towards Robust Vision Transformercited by 137
  21. 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
  22. 2020Smooth Adversarial Trainingcited by 89
  23. 2020Do Wider Neural Networks Really Help Adversarial Robustness?cited by 79
  24. 2020Backpropagating Linearly Improves Transferability of Adversarial Examplescited by 79
  25. 2021Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Bettercited by 79
  26. 2021Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networkscited by 74
  27. 2020Unadversarial Examples: Designing Objects for Robust Visioncited by 45
  28. 2020Practical No-box Adversarial Attacks against DNNscited by 32
  29. 2021Parameterizing Activation Functions for Adversarial Robustnesscited by 22
  30. 2021How and When Adversarial Robustness Transfers in Knowledge Distillation?cited by 16
  31. 2021MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Mapscited by 9
  32. 2020With False Friends Like These, Who Can Notice Mistakes?cited by 4
  33. 2021Bridged Adversarial Trainingcited by 3

Built on by

Cited by year

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

10 papers.

  1. 2024DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domaincited by 12
  2. 2023Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoffcited by 7
  3. 2024Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Trainingcited by 6
  4. 2023Exploring Robust Features for Improving Adversarial Robustnesscited by 4
  5. 2023Improving Transferability of Adversarial Examples via Bayesian Attackscited by 3
  6. 2024Improving Adversarial Training using Vulnerability-Aware Perturbation Budgetcited by 1
  7. 2025Parameter Interpolation Adversarial Training for Robust Image Classificationcited by 1
  8. 2023PIAT: Parameter Interpolation based Adversarial Training for Image Classificationcited by 0
  9. 2024Standard-Deviation-Inspired Regularization for Improving Adversarial Robustnesscited by 0
  10. 2025Nearest Neighbor Projection Removal Adversarial Trainingcited by 0