mlsanityData to 7 Oct 2026

Exploring the Landscape of Spatial Robustness

arXiv 1712.02779 ↗First posted 7 Dec 2017cs.LG cs.CV cs.NEcited by 81

Not on the map. Why?

Abstract (arXiv)

The study of adversarial robustness has so far largely focused on perturbations bound in p-norms. However, state-of-the-art models turn out to be also vulnerable to other, more natural classes of perturbations such as translations and rotations. In this work, we thoroughly investigate the vulnerability of neural network--based classifiers to rotations and translations. While data augmentation offers relatively small robustness, we use ideas from robust optimization and test-time input aggregation to significantly improve robustness. Finally we find that, in contrast to the p-norm case, first-order methods cannot reliably find worst-case perturbations. This highlights spatial robustness as a fundamentally different setting requiring additional study. Code available at https://github.com/MadryLab/adversarial_spatial and https://github.com/MadryLab/spatial-pytorch.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 38; 2022: 11; 2023: 14; 2024: 8; 2025: 7; 2026: 3.

81 papers.

Sort:

By area:

  1. 2021Unsolved Problems in ML Safetycited by 291
  2. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilitycited by 66
  3. 2021CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detectioncited by 64
  4. 2023Black Box Adversarial Prompting for Foundation Modelscited by 62
  5. 2022The Lie Derivative for Measuring Learned Equivariancecited by 51
  6. 2022On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligencecited by 50
  7. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  8. 2025SynthID-Image: Image watermarking at internet scalecited by 26
  9. 2022Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformerscited by 25
  10. 2021Exploring Adversarial Fake Images on Face Manifoldcited by 24
  11. 2021Towards Robust Neural Networks via Close-loop Controlcited by 23
  12. 2021ML Attack Models: Adversarial Attacks and Data Poisoning Attackscited by 23
38 more
  1. 2021Robustness and Generalization via Generative Adversarial Trainingcited by 20
  2. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  3. 2021CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networkscited by 18
  4. 2021Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scalescited by 17
  5. 2023Instruct2Attack: Language-Guided Semantic Adversarial Attackscited by 16
  6. 2021Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Functioncited by 11
  7. 2021Adversarial Token Attacks on Vision Transformerscited by 11
  8. 2023Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learningcited by 11
  9. 2021Truly shift-equivariant convolutional neural networks with adaptive polyphase upsamplingcited by 10
  10. 2024Verification of Neural Networks' Global Robustnesscited by 10
  11. 2021Training or Architecture? How to Incorporate Invariance in Neural Networkscited by 9
  12. 2023Policy Gradient Methods in the Presence of Symmetries and State Abstractionscited by 8
  13. 2024Machine Learning Robustness: A Primercited by 8
  14. 2021Domain Invariant Adversarial Learningcited by 7
  15. 2021SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and sizecited by 7
  16. 2021Imperceptible Adversarial Examples by Spatial Chroma-Shiftcited by 7
  17. 2024A Survey and Evaluation of Adversarial Attacks for Object Detectioncited by 7
  18. 2021Simple Transparent Adversarial Examplescited by 6
  19. 2021Relaxing Local Robustnesscited by 6
  20. 2021Generating Unrestricted Adversarial Examples via Three Parameterscited by 5
  21. 2021Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networkscited by 5
  22. 2021Finding simplicity: unsupervised discovery of features, patterns, and order parameters via shift-invariant variational autoencoderscited by 4
  23. 2022Certified Robustness in Federated Learningcited by 4
  24. 2021Tiny Adversarial Mulit-Objective Oneshot Neural Architecture Searchcited by 3
  25. 2021Adversarial Attack Driven Data Augmentation for Accurate And Robust Medical Image Segmentationcited by 3
  26. 2021In-distribution adversarial attacks on object recognition models using gradient-free searchcited by 3
  27. 2021Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Searchcited by 3
  28. 2023Adversarial Image Generation by Spatial Transformation in Perceptual Colorspacescited by 3
  29. 2024Adversarial Attacks and Defenses in Multivariate Time-Series Forecasting for Smart and Connected Infrastructurescited by 3
  30. 2021Robust Training Using Natural Transformationcited by 2
  31. 2021Probing the Effect of Selection Bias on Generalization: A Thought Experimentcited by 2
  32. 2021Pareto Adversarial Robustness: Balancing Spatial Robustness and Sensitivity-based Robustnesscited by 2
  33. 2022A Simple Strategy to Provable Invariance via Orbit Mappingcited by 2
  34. 2022A Closer Look at Robustness to L-infinity and Spatial Perturbations and their Compositioncited by 2
  35. 2022Assessing Neural Network Robustness via Adversarial Pivotal Tuningcited by 2
  36. 2023A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networkscited by 2
  37. 2021Adversarial Robustness: What fools you makes you strongercited by 1
  38. 2021Localized Uncertainty Attackscited by 1

50 most cited of 81 All 81 (JSON)