mlsanityData to 13 Oct 2026

Certified Defense to Image Transformations via Randomized Smoothing

arXiv 2002.12463 ↗First posted 27 Feb 2020cs.LG cs.CR stat.MLcited by 51

Not on the map. Why?

Abstract (arXiv)

We extend randomized smoothing to cover parameterized transformations (e.g., rotations, translations) and certify robustness in the parameter space (e.g., rotation angle). This is particularly challenging as interpolation and rounding effects mean that image transformations do not compose, in turn preventing direct certification of the perturbed image (unlike certification with ℓp norms). We address this challenge by introducing three different kinds of defenses, each with a different guarantee (heuristic, distributional and individual) stemming from the method used to bound the interpolation error. Importantly, we show how individual certificates can be obtained via either statistical error bounds or efficient online inverse computation of the image transformation. We provide an implementation of all methods at https://github.com/eth-sri/transformation-smoothing.

Key facts. Cited by 51 papers in the map (data through 13 Oct 2026). First posted on arXiv 27 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 12; 2022: 10; 2023: 16; 2024: 6; 2025: 5; 2026: 2.

51 papers.

Sort:

By area:

  1. 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attackscited by 464
  2. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  3. 2021Boosting Randomized Smoothing with Variance Reduced Classifierscited by 47
  4. 2021Improved, Deterministic Smoothing for L_1 Certified Robustnesscited by 39
  5. 2021Scalable Certified Segmentation via Randomized Smoothingcited by 35
  6. 2023Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attackscited by 34
  7. 2021ANCER: Anisotropic Certification via Sample-wise Volume Maximizationcited by 23
  8. 2022GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothingcited by 23
  9. 2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 21
  10. 2021CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networkscited by 18
  11. 2024Provably Unlearnable Data Examplescited by 18
  12. 2021DeformRS: Certifying Input Deformations with Randomized Smoothingcited by 17
38 more
  1. 2021Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselinescited by 17
  2. 2023RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletioncited by 17
  3. 2021Robustness Certification for Point Cloud Modelscited by 16
  4. 2022Provable Defense Against Geometric Transformationscited by 14
  5. 2023Incremental Randomized Smoothing Certificationcited by 12
  6. 2021Input-Specific Robustness Certification for Randomized Smoothingcited by 11
  7. 2023Towards Verifying the Geometric Robustness of Large-scale Neural Networkscited by 11
  8. 2023Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustnesscited by 11
  9. 2021Shared Certificates for Neural Network Verificationcited by 10
  10. 2022TPC: Transformation-Specific Smoothing for Point Cloud Modelscited by 10
  11. 2022Localized Randomized Smoothing for Collective Robustness Certificationcited by 10
  12. 2023Multi-scale Diffusion Denoised Smoothingcited by 9
  13. 2022Private and Reliable Neural Network Inferencecited by 7
  14. 2022Invariance-Aware Randomized Smoothing Certificatescited by 7
  15. 2024Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisationcited by 7
  16. 2021Certified Robustness via Randomized Smoothing over Multiplicative Parameters of Input Transformationscited by 6
  17. 2022Certifying Model Accuracy under Distribution Shiftscited by 5
  18. 2022(De-)Randomized Smoothing for Decision Stump Ensemblescited by 5
  19. 2023OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networkscited by 5
  20. 2023A Certified Radius-Guided Attack Framework to Image Segmentation Modelscited by 5
  21. 2023Training on Foveated Images Improves Robustness to Adversarial Attackscited by 5
  22. 2023Precise and Generalized Robustness Certification for Neural Networkscited by 4
  23. 2024Estimating the Robustness Radius for Randomized Smoothing with 100× Sample Efficiencycited by 4
  24. 2024RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothingcited by 4
  25. 2022Robustness Certification of Visual Perception Models via Camera Motion Smoothingcited by 3
  26. 2023On the Fly Neural Style Smoothing for Risk-Averse Domain Generalizationcited by 3
  27. 2022A Simple Strategy to Provable Invariance via Orbit Mappingcited by 2
  28. 2023Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbationscited by 2
  29. 2025Reconcile Certified Robustness and Accuracy for DNN-based Smoothed Majority Vote Classifiercited by 2
  30. 2024Accelerated Smoothing: A Scalable Approach to Randomized Smoothingcited by 1
  31. 2024Certified Robustness against Sparse Adversarial Perturbations via Data Localizationcited by 1
  32. 2025CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximizationcited by 1
  33. 2025Randomized Smoothing Meets Vision-Language Modelscited by 1
  34. 2023Fixed Inter-Neuron Covariability Induces Adversarial Robustnesscited by 0
  35. 2023General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothingcited by 0
  36. 2025Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifierscited by 0
  37. 2025Cumulative Consensus Score: Label-Free and Model-Agnostic Evaluation of Object Detectors in Deploymentcited by 0
  38. 2026RRISE: Robust Radius Inference via a Surrogate Estimatorcited by 0

50 most cited of 51 All 51 (JSON)