mlsanityData to 7 Oct 2026

Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack

arXiv 1907.02044 ↗First posted 3 Jul 2019cs.LG cs.CR cs.CVcited by 333

Not on the map. Why?

Abstract (arXiv)

The evaluation of robustness against adversarial manipulation of neural networks-based classifiers is mainly tested with empirical attacks as methods for the exact computation, even when available, do not scale to large networks. We propose in this paper a new white-box adversarial attack wrt the lp-norms for p ∈ 1,2,∞ aiming at finding the minimal perturbation necessary to change the class of a given input. It has an intuitive geometric meaning, yields quickly high quality results, minimizes the size of the perturbation (so that it returns the robust accuracy at every threshold with a single run). It performs better or similar to state-of-the-art attacks which are partially specialized to one lp-norm, and is robust to the phenomenon of gradient masking.

Key facts. Cited by 333 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 55; 2022: 71; 2023: 80; 2024: 62; 2025: 49; 2026: 16.

333 papers.

Sort:

By area:

  1. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  2. 2021Data Augmentation Can Improve Robustnesscited by 193
  3. 2021Are Transformers More Robust Than CNNs?cited by 187
  4. 2021On the Adversarial Robustness of Vision Transformerscited by 104
  5. 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 94
  6. 2021Trustworthy AI: A Computational Perspectivecited by 93
  7. 2021Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attackscited by 91
  8. 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
  9. 2021RobustART: Benchmarking Robustness on Architecture Design and Training Techniquescited by 78
  10. 2021Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Bettercited by 77
  11. 2021Improving Adversarial Robustness via Channel-wise Activation Suppressingcited by 76
  12. 2021On Improving Adversarial Transferability of Vision Transformerscited by 70
38 more
  1. 2023Robust Evaluation of Diffusion-Based Adversarial Purificationcited by 65
  2. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
  3. 2022A Light Recipe to Train Robust Vision Transformerscited by 64
  4. 2022When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecturecited by 64
  5. 2023A Unified Algebraic Perspective on Lipschitz Neural Networkscited by 58
  6. 2021Exploring Memorization in Adversarial Trainingcited by 55
  7. 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
  8. 2021Mind the box: l1-APGD for sparse adversarial attacks on image classifierscited by 50
  9. 2022Understanding Robust Overfitting of Adversarial Training and Beyondcited by 50
  10. 2021Adversarial Attacks are Reversible with Natural Supervisioncited by 47
  11. 2022Practical Evaluation of Adversarial Robustness via Adaptive Auto Attackcited by 44
  12. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  13. 2021Reveal of Vision Transformers Robustness against Adversarial Attackscited by 43
  14. 2022Enhancing Adversarial Training with Second-Order Statistics of Weightscited by 42
  15. 2021Boosting Fast Adversarial Training with Learnable Adversarial Initializationcited by 40
  16. 2021Partition-based formulations for mixed-integer optimization of trained ReLU neural networkscited by 39
  17. 2022A Unified Wasserstein Distributional Robustness Framework for Adversarial Trainingcited by 36
  18. 2023Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustnesscited by 35
  19. 2021GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularizationcited by 34
  20. 2022OMLT: Optimization & Machine Learning Toolkitcited by 34
  21. 2022Prior-Guided Adversarial Initialization for Fast Adversarial Trainingcited by 34
  22. 2023Improving Fast Adversarial Training with Prior-Guided Knowledgecited by 34
  23. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  24. 2024Revisiting Adversarial Training at Scalecited by 33
  25. 2021Attacking Adversarial Attacks as A Defensecited by 31
  26. 2022Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneckcited by 30
  27. 2021Reliably fast adversarial training via latent adversarial perturbationcited by 29
  28. 2023Improving Adversarial Transferability via Intermediate-level Perturbation Decaycited by 29
  29. 2023Randomized Adversarial Training via Taylor Expansioncited by 28
  30. 2021Combating Adversaries with Anti-Adversariescited by 27
  31. 2021Enhancing Adversarial Robustness via Test-time Transformation Ensemblingcited by 27
  32. 2021Towards Understanding the Generative Capability of Adversarially Robust Classifierscited by 26
  33. 2021Learning to Break Deep Perceptual Hashing: The Use Case NeuralHashcited by 25
  34. 2022Restricted Black-box Adversarial Attack Against DeepFake Face Swappingcited by 25
  35. 2021LAFEAT: Piercing Through Adversarial Defenses with Latent Featurescited by 24
  36. 2022Fast Adversarial Training with Adaptive Step Sizecited by 24
  37. 2024On the Duality Between Sharpness-Aware Minimization and Adversarial Trainingcited by 24
  38. 2021Removing Undesirable Feature Contributions Using Out-of-Distribution Datacited by 23

50 most cited of 333 All 333 (JSON)