mlsanityData to 14 Oct 2026

Scalable Certified Segmentation via Randomized Smoothing

arXiv 2107.00228 ↗First posted 1 Jul 2021cs.LG cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

We present a new certification method for image and point cloud segmentation based on randomized smoothing. The method leverages a novel scalable algorithm for prediction and certification that correctly accounts for multiple testing, necessary for ensuring statistical guarantees. The key to our approach is reliance on established multiple-testing correction mechanisms as well as the ability to abstain from classifying single pixels or points while still robustly segmenting the overall input. Our experimental evaluation on synthetic data and challenging datasets, such as Pascal Context, Cityscapes, and ShapeNet, shows that our algorithm can achieve, for the first time, competitive accuracy and certification guarantees on real-world segmentation tasks. We provide an implementation at https://github.com/eth-sri/segmentation-smoothing.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). Builds on 44 of its 72 references that are in the map. First posted on arXiv 1 Jul 2021.

Builds on

44 of 72 references.

References · 44

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  9. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  10. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  11. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  12. 2016Adversarial Machine Learning at Scalecited by 936
32 more
  1. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  2. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  3. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  4. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  5. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
  6. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 330
  7. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
  8. 2018Certified Defenses against Adversarial Examplescited by 306
  9. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  10. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 255
  11. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 242
  12. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  13. 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 179
  14. 2018Efficient Formal Safety Analysis of Neural Networkscited by 165
  15. 2020Randomized Smoothing of All Shapes and Sizescited by 147
  16. 2018Generating 3D Adversarial Point Cloudscited by 144
  17. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  18. 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
  19. 2020(De)Randomized Smoothing for Certifiable Defense against Patch Attackscited by 98
  20. 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
  21. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  22. 2020Consistency Regularization for Certified Robustness of Smoothed Classifierscited by 73
  23. 2020Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and Morecited by 56
  24. 2020Certified Defense to Image Transformations via Randomized Smoothingcited by 51
  25. 2020TSS: Transformation-Specific Smoothing for Robustness Certificationcited by 49
  26. 2020Detection as Regression: Certified Object Detection by Median Smoothingcited by 47
  27. 2020Adversarial Robustness for Codecited by 38
  28. 2020Higher-Order Certification for Randomized Smoothingcited by 37
  29. 2019Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attackscited by 25
  30. 2021Robustness Certification for Point Cloud Modelscited by 16
  31. 2020Efficient Certification of Spatial Robustnesscited by 11
  32. 2017Spinal cord gray matter segmentation using deep dilated convolutionscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 10; 2024: 6; 2025: 6; 2026: 3.

35 papers.

Sort:

By area:

  1. 2023Certifying LLM Safety against Adversarial Promptingcited by 266
  2. 2022Certified Defences Against Adversarial Patch Attacks on Semantic Segmentationcited by 16
  3. 2021Adversarial Examples on Segmentation Models Can be Easy to Transfercited by 15
  4. 2023Unlocking Deterministic Robustness Certification on ImageNetcited by 13
  5. 2023Incremental Randomized Smoothing Certificationcited by 12
  6. 2022TPC: Transformation-Specific Smoothing for Point Cloud Modelscited by 10
  7. 2022Localized Randomized Smoothing for Collective Robustness Certificationcited by 10
  8. 2023TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentationcited by 10
  9. 2022Confidence-aware Training of Smoothed Classifiers for Certified Robustnesscited by 9
  10. 2023Node-aware Bi-smoothing: Certified Robustness against Graph Injection Attackscited by 8
  11. 2022Private and Reliable Neural Network Inferencecited by 7
  12. 2022Invariance-Aware Randomized Smoothing Certificatescited by 7
23 more
  1. 2024Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisationcited by 7
  2. 2023PointCert: Point Cloud Classification with Deterministic Certified Robustness Guaranteescited by 6
  3. 2022(De-)Randomized Smoothing for Decision Stump Ensemblescited by 5
  4. 2023A Certified Radius-Guided Attack Framework to Image Segmentation Modelscited by 5
  5. 2023Certification of Deep Learning Models for Medical Image Segmentationcited by 5
  6. 2026Certified Circuits: Stability Guarantees for Mechanistic Circuitscited by 5
  7. 2024MMCert: Provable Defense against Adversarial Attacks to Multi-modal Modelscited by 4
  8. 2024Estimating the Robustness Radius for Randomized Smoothing with 100× Sample Efficiencycited by 4
  9. 2025Pixel-level Certified Explanations via Randomized Smoothingcited by 4
  10. 2025One Sample is Enough to Make Conformal Prediction Robustcited by 4
  11. 2024Adaptive Hierarchical Certification for Segmentation using Randomized Smoothingcited by 3
  12. 2022Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysiscited by 2
  13. 2023Towards Better Certified Segmentation via Diffusion Modelscited by 2
  14. 2025Reconcile Certified Robustness and Accuracy for DNN-based Smoothed Majority Vote Classifiercited by 2
  15. 2024Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothingcited by 1
  16. 2025Randomized Smoothing Meets Vision-Language Modelscited by 1
  17. 2025Fast and Flexible Robustness Certificates for Semantic Segmentationcited by 1
  18. 2022Robustness Evaluation and Adversarial Training of an Instance Segmentation Modelcited by 0
  19. 2023STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformerscited by 0
  20. 2024Certified Adversarial Robustness via Partition-based Randomized Smoothingcited by 0
  21. 2025Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifierscited by 0
  22. 2026Certified geometric robustness -- Super-DeepGcited by 0
  23. 2026NNV3: Expanding Neural Network Verification to New Architectures and Domainscited by 0