mlsanityData to 7 Oct 2026

Impact of Attention on Adversarial Robustness of Image Classification Models

arXiv 2109.00936 ↗First posted 2 Sep 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks against deep learning models have gained significant attention and recent works have proposed explanations for the existence of adversarial examples and techniques to defend the models against these attacks. Attention in computer vision has been used to incorporate focused learning of important features and has led to improved accuracy. Recently, models with attention mechanisms have been proposed to enhance adversarial robustness. Following this context, this work aims at a general understanding of the impact of attention on adversarial robustness. This work presents a comparative study of adversarial robustness of non-attention and attention based image classification models trained on CIFAR-10, CIFAR-100 and Fashion MNIST datasets under the popular white box and black box attacks. The experimental results show that the robustness of attention based models may be dependent on the datasets used i.e. the number of classes involved in the classification. In contrast to the datasets with less number of classes, attention based models are observed to show better robustness towards classification.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 32 of its 35 references that are in the map. First posted on arXiv 2 Sep 2021.

Builds on

32 of 35 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  9. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  10. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  11. 2017Countering Adversarial Images using Input Transformationscited by 517
  12. 2017Residual Attention Network for Image Classificationcited by 385
20 more
  1. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  2. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  3. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  4. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  5. 2020Exploring Self-attention for Image Recognitioncited by 313
  6. 2018Certified Defenses against Adversarial Examplescited by 305
  7. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  8. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  9. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  10. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  11. 2018Scaling provable adversarial defensescited by 141
  12. 2018Adversarial Attacks and Defences Competitioncited by 96
  13. 2018Adversarial examples from computational constraintscited by 79
  14. 2018Training for Faster Adversarial Robustness Verification via Inducing ReLU Stabilitycited by 67
  15. 2019Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attackscited by 54
  16. 2019Towards Robust Image Classification Using Sequential Attention Modelscited by 27
  17. 2021Modality specific U-Net variants for biomedical image segmentation: A surveycited by 20
  18. 2018Feature Prioritization and Regularization Improve Standard Accuracy and Adversarial Robustnesscited by 5
  19. 2019Can Attention Masks Improve Adversarial Robustness?cited by 5
  20. 2019Improving Adversarial Robustness via Attention and Adversarial Logit Pairingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 0; 2024: 0; 2025: 0; 2026: 1.

4 papers.

  1. 2022Anomaly detection in surveillance videos using transformer based attention modelcited by 4
  2. 2022Enhancing Classifier Conservativeness and Robustness by Polynomialitycited by 1
  3. 2022Adversarially Robust Medical Classification via Attentive Convolutional Neural Networkscited by 0
  4. 2026Threats to Arabic Handwriting Recognition: Investigating Black-Box Adversarial Attacks on embedded ConvNet modelscited by 0