mlsanityData to 7 Oct 2026

Pixle: a fast and effective black-box attack based on rearranging pixels

arXiv 2202.02236 ↗First posted 4 Feb 2022cs.LG stat.MLcited by 20

Not on the map. Why?

Abstract (arXiv)

Recent research has found that neural networks are vulnerable to several types of adversarial attacks, where the input samples are modified in such a way that the model produces a wrong prediction that misclassifies the adversarial sample. In this paper we focus on black-box adversarial attacks, that can be performed without knowing the inner structure of the attacked model, nor the training procedure, and we propose a novel attack that is capable of correctly attacking a high percentage of samples by rearranging a small number of pixels within the attacked image. We demonstrate that our attack works on a large number of datasets and models, that it requires a small number of iterations, and that the distance between the original sample and the adversarial one is negligible to the human eye.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 4 Feb 2022.

Builds on

21 of 33 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  8. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  9. 2017One pixel attack for fooling deep neural networkscited by 579
  10. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  11. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  12. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
9 more
  1. 2020Torchattacks: A PyTorch Repository for Adversarial Attackscited by 156
  2. 2018SparseFool: a few pixels make a big differencecited by 94
  3. 2018GenAttack: Practical Black-box Attacks with Gradient-Free Optimizationcited by 82
  4. 2015Learning with a Strong Adversarycited by 68
  5. 2020PatchAttack: A Black-box Texture-based Attack with Reinforcement Learningcited by 67
  6. 2017Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reductioncited by 49
  7. 2019A Survey of Black-Box Adversarial Attacks on Computer Vision Modelscited by 36
  8. 2017Attacking the Madry Defense Model with L1-based Adversarial Examplescited by 21
  9. 2019Scratch that! An Evolution-based Adversarial Attack against Neural Networkscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 9; 2025: 7; 2026: 3.

20 papers.

Sort:

By area:

  1. 2024On the Duality Between Sharpness-Aware Minimization and Adversarial Trainingcited by 24
  2. 2025Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspectivecited by 10
  3. 2024Multimodal Attack Detection for Action Recognition Modelscited by 5
  4. 2025Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuningcited by 5
  5. 2024Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectorscited by 3
  6. 2025Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filterscited by 3
  7. 2023Towards Certified Probabilistic Robustness with High Accuracycited by 2
  8. 2024Improving Adversarial Robustness via Decoupled Visual Representation Maskingcited by 2
  9. 2024SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledgecited by 1
  10. 2024Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decompositioncited by 1
  11. 2025How to Backdoor Image Knowledge Distillationcited by 1
  12. 2025Adversarially Robust AI-Generated Image Detection for Free: An Information Theoretic Perspectivecited by 1
8 more
  1. 2024Active Fake: DeepFake Camouflagecited by 0
  2. 2024Hidden Activations Are Not Enough: A General Approach to Neural Network Predictionscited by 0
  3. 2024Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noisescited by 0
  4. 2025IGAff: Benchmarking Adversarial Iterative and Genetic Affine Algorithms on Deep Neural Networkscited by 0
  5. 2025A Modern Look at Simplicity Bias in Image Classification Taskscited by 0
  6. 2026Emotion Diffusion Classifier with Adaptive Margin Discrepancy Training for Facial Expression Recognitioncited by 0
  7. 2026Threats to Arabic Handwriting Recognition: Investigating Black-Box Adversarial Attacks on embedded ConvNet modelscited by 0
  8. 2026Updating the standard neuron model in artificial neural networkscited by 0