mlsanityData to 7 Oct 2026

Sparse and Imperceivable Adversarial Attacks

arXiv 1909.05040 ↗First posted 11 Sep 2019cs.LG cs.CR cs.CVcited by 95

Not on the map. Why?

Abstract (arXiv)

Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks are typically large and thus can be potentially detected. We propose a new black-box technique to craft adversarial examples aiming at minimizing l0-distance to the original image. Extensive experiments show that our attack is better or competitive to the state of the art. Moreover, we can integrate additional bounds on the componentwise perturbation. Allowing pixels to change only in region of high variation and avoiding changes along axis-aligned edges makes our adversarial examples almost non-perceivable. Moreover, we adapt the Projected Gradient Descent attack to the l0-norm integrating componentwise constraints. This allows us to do adversarial training to enhance the robustness of classifiers against sparse and imperceivable adversarial manipulations.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 24; 2023: 16; 2024: 19; 2025: 10; 2026: 6.

95 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
  3. 2022Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?cited by 47
  4. 2021AVA: Adversarial Vignetting Attack against Visual Recognitioncited by 29
  5. 2022One-Pixel Shortcut: on the Learning Preference of Deep Neural Networkscited by 29
  6. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 24
  7. 2023Backdoor Attack with Sparse and Invisible Triggercited by 20
  8. 2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 19
  9. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  10. 2024UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Modelscited by 18
  11. 2021Attack to Fool and Explain Deep Networkscited by 17
  12. 2021Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attackscited by 16
38 more
  1. 2021Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithmcited by 15
  2. 2022Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defensecited by 14
  3. 2022Towards Good Practices in Evaluating Transfer Adversarial Attackscited by 14
  4. 2024AttackBench: Evaluating Gradient-based Attacks for Adversarial Examplescited by 14
  5. 2022Query Efficient Decision Based Sparse Attacks Against Black-Box Deep Learning Modelscited by 13
  6. 2023Less is More: Data Pruning for Faster Adversarial Trainingcited by 13
  7. 2022Saliency Attack: Towards Imperceptible Black-box Adversarial Attackcited by 12
  8. 2022Imperceptible Adversarial Attack via Invertible Neural Networkscited by 12
  9. 2024Understanding Robustness of Visual State Space Models for Image Classificationcited by 12
  10. 2021Adversarial Token Attacks on Vision Transformerscited by 11
  11. 2021Transferable Sparse Adversarial Attackcited by 9
  12. 2023Hierarchical Randomized Smoothingcited by 9
  13. 2021PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attackcited by 8
  14. 2021Adversarial Attack and Defense in Deep Rankingcited by 8
  15. 2022fakeWeather: Adversarial Attacks for Deep Neural Networks Emulating Weather Conditions on the Camera Lens of Autonomous Systemscited by 8
  16. 2022Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanismscited by 8
  17. 2024Imperceptible Protection against Style Imitation from Diffusion Modelscited by 8
  18. 2022AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classificationcited by 7
  19. 2023RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Modelscited by 7
  20. 2024σ-zero: Gradient-based Optimization of ℓ0-norm Adversarial Examplescited by 7
  21. 2024BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attackcited by 7
  22. 2021Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Acceleratorscited by 6
  23. 2021Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attackscited by 6
  24. 2023Optimization and Optimizers for Adversarial Robustnesscited by 6
  25. 2023SoK: Pitfalls in Evaluating Black-Box Attackscited by 6
  26. 2022Adversarial Scratches: Deployable Attacks to CNN Classifierscited by 5
  27. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  28. 2023GSE: Group-wise Sparse and Explainable Adversarial Attackscited by 5
  29. 2021Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Taskscited by 4
  30. 2021The Fundamental Limits of Interval Arithmetic for Neural Networkscited by 4
  31. 2022On the interplay of adversarial robustness and architecture components: patches, convolution and attentioncited by 4
  32. 2024IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metricscited by 4
  33. 2024Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generationcited by 4
  34. 2024Investigating Imperceptibility of Adversarial Attacks on Tabular Data: An Empirical Analysiscited by 4
  35. 2024Low-Rank Adversarial PGD Attackcited by 4
  36. 2021Lagrangian Objective Function Leads to Improved Unforeseen Attack Generalization in Adversarial Trainingcited by 3
  37. 2021An Overview of Laser Injection against Embedded Neural Network Modelscited by 3
  38. 2021Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classescited by 3

50 most cited of 95 All 95 (JSON)