mlsanityData to 14 Oct 2026

Exploring Adversarial Robustness of Vision Transformers in the Spectral Perspective

arXiv 2208.09602 ↗First posted 20 Aug 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

The Vision Transformer has emerged as a powerful tool for image classification tasks, surpassing the performance of convolutional neural networks (CNNs). Recently, many researchers have attempted to understand the robustness of Transformers against adversarial attacks. However, previous researches have focused solely on perturbations in the spatial domain. This paper proposes an additional perspective that explores the adversarial robustness of Transformers against frequency-selective perturbations in the spectral domain. To facilitate comparison between these two domains, an attack framework is formulated as a flexible tool for implementing attacks on images in the spatial and spectral domains. The experiments reveal that Transformers rely more on phase and low frequency information, which can render them more vulnerable to frequency-selective attacks than CNNs. This work offers new insights into the properties and adversarial robustness of Transformers.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 34 of its 48 references that are in the map. First posted on arXiv 20 Aug 2022.

Builds on

34 of 48 references.

References · 34

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  10. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  11. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  12. 2020Quantifying Attention Flow in Transformerscited by 775
22 more
  1. 2021Transformer in Transformercited by 633
  2. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  3. 2021Intriguing Properties of Vision Transformerscited by 446
  4. 2021XCiT: Cross-Covariance Image Transformerscited by 338
  5. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  6. 2022How Do Vision Transformers Work?cited by 307
  7. 2021Understanding Robustness of Transformers for Image Classificationcited by 249
  8. 2021Vision Transformers are Robust Learnerscited by 207
  9. 2021Are Transformers More Robust Than CNNs?cited by 187
  10. 2021On the Robustness of Vision Transformers to Adversarial Examplescited by 167
  11. 2018LaVAN: Localized and Visible Adversarial Noisecited by 113
  12. 2021On the Adversarial Robustness of Vision Transformerscited by 106
  13. 2017Measuring the tendency of CNNs to Learn Surface Statistical Regularitiescited by 87
  14. 2018Low Frequency Adversarial Perturbationcited by 80
  15. 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 71
  16. 2021Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNscited by 57
  17. 2019On the Effectiveness of Low Frequency Perturbationscited by 56
  18. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 56
  19. 2022Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?cited by 49
  20. 2021Reveal of Vision Transformers Robustness against Adversarial Attackscited by 43
  21. 2021Are Vision Transformers Robust to Patch Perturbations?cited by 39
  22. 2016Mean Deviation Similarity Index: Efficient and Reliable Full-Reference Image Quality Evaluatorcited by 32

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 6; 2026: 1.

8 papers.

  1. 2025FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEctioncited by 11
  2. 2025Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspectivecited by 10
  3. 2025Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Modelscited by 6
  4. 2022Game-Theoretic Understanding of Misclassificationcited by 2
  5. 2025TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularizationcited by 2
  6. 2025Defending Against Frequency-Based Attacks with Diffusion Modelscited by 1
  7. 2025Boosting Adversarial Transferability via Commonality-Oriented Gradient Optimizationcited by 1
  8. 2026In Transformer We Trust? A Perspective on Transformer Architecture Failure Modescited by 1