mlsanityData to 14 Oct 2026

ADef: an Iterative Algorithm to Construct Adversarial Deformations

arXiv 1804.07729 ↗First posted 20 Apr 2018cs.CV cs.CR cs.LGcited by 38

Not on the map. Why?

Abstract (arXiv)

While deep neural networks have proven to be a powerful tool for many recognition and classification tasks, their stability properties are still not well understood. In the past, image classifiers have been shown to be vulnerable to so-called adversarial attacks, which are created by additively perturbing the correctly classified image. In this paper, we propose the ADef algorithm to construct a different kind of adversarial attack created by iteratively applying small deformations to the image, found through a gradient descent step. We demonstrate our results on MNIST with convolutional neural networks and on ImageNet with Inception-v3 and ResNet-101.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 8; 2023: 5; 2024: 4; 2025: 4; 2026: 1.

38 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2021On the Adversarial Robustness of Vision Transformerscited by 106
  3. 2023Content-based Unrestricted Adversarial Attackcited by 73
  4. 20213D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detectioncited by 43
  5. 2025SynthID-Image: Image watermarking at internet scalecited by 31
  6. 2021Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentationcited by 20
  7. 2021Robustness and Generalization via Generative Adversarial Trainingcited by 20
  8. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  9. 2021DeformRS: Certifying Input Deformations with Randomized Smoothingcited by 17
  10. 2022Towards Good Practices in Evaluating Transfer Adversarial Attackscited by 15
  11. 2022Towards Transferable Unrestricted Adversarial Examples with Minimum Changescited by 13
  12. 2021Relative stability toward diffeomorphisms indicates performance in deep netscited by 12
26 more
  1. 2023Towards Verifying the Geometric Robustness of Large-scale Neural Networkscited by 11
  2. 2021Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Trainingcited by 10
  3. 2021Domain Invariant Adversarial Learningcited by 7
  4. 2021Imperceptible Adversarial Examples by Spatial Chroma-Shiftcited by 7
  5. 2024How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Modelcited by 7
  6. 2021Generating Unrestricted Adversarial Examples via Three Parameterscited by 5
  7. 2022How deep convolutional neural networks lose spatial information with trainingcited by 5
  8. 2021Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Networkcited by 4
  9. 2023Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspectivecited by 4
  10. 20233D Adversarial Augmentations for Robust Out-of-Domain Predictionscited by 4
  11. 2024The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspectivecited by 4
  12. 2021Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Searchcited by 3
  13. 2022Stability of the scattering transform for deformations with minimal regularitycited by 3
  14. 2024SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM Inversioncited by 3
  15. 2025Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignmentcited by 3
  16. 2025Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generationcited by 3
  17. 2025When Flatness Does (Not) Guarantee Adversarial Robustnesscited by 3
  18. 2021Learning Defense Transformers for Counterattacking Adversarial Examplescited by 2
  19. 2021Sparta: Spatially Attentive and Adversarially Robust Activationcited by 2
  20. 2022Adversarial Attack and Defense for Non-Parametric Two-Sample Testscited by 2
  21. 2022Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimizationcited by 2
  22. 2022Localized adversarial artifacts for compressed sensing MRIcited by 2
  23. 2022Assessing Neural Network Robustness via Adversarial Pivotal Tuningcited by 2
  24. 2021Internal Wasserstein Distance for Adversarial Attack and Defensecited by 1
  25. 2024Distortion-Aware Adversarial Attacks on Bounding Boxes of Object Detectorscited by 1
  26. 2026Adversarial Evasion Attacks on Computer Vision using SHAP Valuescited by 0