Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 205

The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.

On the Robustness of Vision Transformers to Adversarial Examples

Open access
Mahmood, Kaleel, Mahmood, Rigel, van Dijk, Marten · 2021 · 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Abstract

Recent advances in attention-based networks have shown that Vision Transformers can achieve state-of-the-art or near state-of-the-art results on many image classification tasks. This puts transformers in the unique position of being a promising alternative to traditional convolutional neural networks (CNNs). While CNNs have been carefully studied with respect to adversarial attacks, the same cannot be said of Vision Transformers. In this paper, we study the robustness of Vision Transformers to adversarial examples. Our analyses of transformer security is divided into three parts. First, we test the transformer under standard white-box and black-box attacks. Second, we study the transfer-ability of adversarial examples between CNNs and trans-formers. We show that adversarial examples do not readily transfer between CNNs and transformers. Based on this finding, we analyze the security of a simple ensemble defense of CNNs and transformers. By creating a new attack, the self-attention blended gradient attack, we show that such an ensemble is not secure under a white-box adversary. However, under a black-box adversary, we show that an ensemble can achieve unprecedented robustness without sacrificing clean accuracy. Our analysis for this work is done using six types of white-box attacks and two types of black-box attacks. Our study encompasses multiple Vision Transformers, Big Transfer Models and CNN architectures trained on CIFAR-10, CIFAR-100 and ImageNet.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/iccv48922.2021.00774

Cites

21 of 21 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 21 references

Research works printed but not linked: 18

  1. zhang, 2020, Attacks which do not kill training make adversarial learning stronger, International Conference on Machine Learning, 11278
  2. srisakaokul, 2018, Muldef:Multi-model-based defense against adversarial examples for neural networks, arXiv preprint arXiv 1809 00065
  3. shi, 0, Robustness verification for transformers, ICLR 2020
  4. wang, 2020, Axial-deeplab:Stand-alone axial-attention for panoptic segmentation, European Conference on Computer Vision, 108
  5. vaswani, 2017, Attention is all you need
  6. croce, 2020, Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks, International Conference on Machine Learning, 2206
  7. 10.1109/CVPR.2018.00957 · DOI · Paper page
  8. goodfellow, 2015, Explaining and harnessing adversarial examples, Inter-national Conference on Learning Representations
  9. hao, 2020, Self-attention attribution:Interpreting information interactions inside transformer, arXiv preprint arXiv 2004 12027
  10. 10.18653/v1/2020.acl-main.244 · DOI · Paper page
  11. papernot, 2016, Transferability in machine learning:from phenomena to black-box attacks using adversarial samples, arXiv preprint arXiv 1605 07761
  12. pang, 2019, Improving Adversarial Robustness via Promoting Ensemble Diversity, ICML, 4970
  13. carlini, 2019, On evaluating adversarial robustness
  14. 10.1145/3394486.3403225 · DOI
  15. carlini, 2016, Towards Evaluating the Robustness of Neural Networks, CoRR
  16. cordonnier, 2020, On the relationship between self-attention and convolutional layers, International Conference on Learning Representations
  17. liu, 2016, Delving into transferable adversarial examples and black-box attacks, arXiv preprint arXiv 1611 02770
  18. madry, 2018, Towards deep learning models resistant to adversarial attacks, International Conference on Learning Representations

Cited by

See all 205

Metadata

Authors
Mahmood, K., Mahmood, R., & van Dijk, M.
Venue
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2021-10
Pages
7818-7827
OpenAlex
W3143373604
Cited by
205
References
21
FWCI
17.28
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: On the Robustness of Vision Transformers to Adversarial Examples. https://app.cochat.ai/papers/10.1109/iccv48922.2021.00774
The paper
Mahmood, K., Mahmood, R., & van Dijk, M. (2021). On the Robustness of Vision Transformers to Adversarial Examples. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv48922.2021.00774

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.