mlsanityData to 7 Oct 2026

ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches

arXiv 2203.04412 ↗First posted 7 Mar 2022cs.CR cs.CV cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it. However, their optimization is computationally demanding, and requires careful hyperparameter tuning, potentially leading to suboptimal robustness evaluations. To overcome these issues, we propose ImageNet-Patch, a dataset to benchmark machine-learning models against adversarial patches. It consists of a set of patches, optimized to generalize across different models, and readily applicable to ImageNet data after preprocessing them with affine transformations. This process enables an approximate yet faster robustness evaluation, leveraging the transferability of adversarial perturbations. We showcase the usefulness of this dataset by testing the effectiveness of the computed patches against 127 models. We conclude by discussing how our dataset could be used as a benchmark for robustness, and how our methodology can be generalized to other domains. We open source our dataset and evaluation code at https://github.com/pralab/ImageNet-Patch.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 7 Mar 2022.

Builds on

30 of 45 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2014Going Deeper with Convolutionscited by 4,231
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  8. 2019Searching for MobileNetV3cited by 1,984
  9. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  10. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  11. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  12. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
18 more
  1. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  2. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  3. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  4. 2017Adversarial Patchcited by 514
  5. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 452
  6. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  7. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  8. 2019Billion-scale semi-supervised learning for image classificationcited by 232
  9. 2018LaVAN: Localized and Visible Adversarial Noisecited by 112
  10. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 92
  11. 2021Improving Transferability of Adversarial Patches on Face Recognition with Generative Modelscited by 80
  12. 2021RobustART: Benchmarking Robustness on Architecture Design and Training Techniquescited by 78
  13. 2020PatchAttack: A Black-box Texture-based Attack with Reinforcement Learningcited by 67
  14. 2019APRICOT: A Dataset of Physical Adversarial Attacks on Object Detectioncited by 30
  15. 2020Double Targeted Universal Adversarial Perturbationscited by 23
  16. 2021Generative Dynamic Patch Attackcited by 19
  17. 2021Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devicescited by 18
  18. 2021Patch Attack Invariance: How Sensitive are Patch Attacks to 3D Pose?cited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 10; 2024: 5; 2025: 7; 2026: 1.

27 papers.

Sort:

By area:

  1. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  2. 2024The Entropy Enigma: Success and Failure of Entropy Minimizationcited by 24
  3. 2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 20
  4. 2022REAP: A Large-Scale Realistic Adversarial Patch Benchmarkcited by 17
  5. 2023Classification robustness to common optical aberrationscited by 13
  6. 2022CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Modelscited by 8
  7. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 8
  8. 2023Benchmarking Robustness to Adversarial Image Obfuscationscited by 8
  9. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  10. 2024Multimodal Attack Detection for Action Recognition Modelscited by 5
  11. 2025Don't Lag, RAG: Training-Free Adversarial Detection Using RAGcited by 5
  12. 2023A Red Teaming Framework for Securing AI in Maritime Autonomous Systemscited by 3
15 more
  1. 2025Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptionscited by 3
  2. 2024A Survey of Neural Network Robustness Assessment in Image Recognitioncited by 2
  3. 2025Examining the Impact of Optical Aberrations to Image Classification and Object Detection Modelscited by 2
  4. 2022Synthetic Dataset Generation for Adversarial Machine Learning Researchcited by 1
  5. 2023Mithridates: Auditing and Boosting Backdoor Resistance of Machine Learning Pipelinescited by 1
  6. 2023Fight Fire with Fire: Combating Adversarial Patch Attacks using Pattern-randomized Defensive Patchescited by 1
  7. 2025Unveiling Hidden Vulnerabilities in Digital Human Generation via Adversarial Attackscited by 1
  8. 2023The race to robustness: exploiting fragile models for urban camouflage and the imperative for machine learning securitycited by 0
  9. 2023Assist Is Just as Important as the Goal: Image Resurfacing to Aid Model's Robust Predictioncited by 0
  10. 2024Topological safeguard for evasion attack interpreting the neural networks' behaviorcited by 0
  11. 2024The Anatomy of Adversarial Attacks: Concept-based XAI Dissectioncited by 0
  12. 2025FRAUD-RLA: A new reinforcement learning adversarial attack against credit card fraud detectioncited by 0
  13. 2025EasyRobust: A Comprehensive and Easy-to-use Toolkit for Robust and Generalized Visioncited by 0
  14. 2025SpaNN: Detecting Multiple Adversarial Patches on CNNs by Spanning Saliency Thresholdscited by 0
  15. 2026The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patchescited by 0