mlsanityData to 14 Oct 2026

Invariance-Aware Randomized Smoothing Certificates

arXiv 2211.14207 ↗First posted 25 Nov 2022cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Building models that comply with the invariances inherent to different domains, such as invariance under translation or rotation, is a key aspect of applying machine learning to real world problems like molecular property prediction, medical imaging, protein folding or LiDAR classification. For the first time, we study how the invariances of a model can be leveraged to provably guarantee the robustness of its predictions. We propose a gray-box approach, enhancing the powerful black-box randomized smoothing technique with white-box knowledge about invariances. First, we develop gray-box certificates based on group orbits, which can be applied to arbitrary models with invariance under permutation and Euclidean isometries. Then, we derive provably tight gray-box certificates. We experimentally demonstrate that the provably tight certificates can offer much stronger guarantees, but that in practical scenarios the orbit-based method is a good approximation.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 83 of its 142 references that are in the map. First posted on arXiv 25 Nov 2022.

Builds on

83 of 142 references.

References · 83

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  8. 2017Deep Setscited by 1,421
  9. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  10. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  11. 2016Group Equivariant Convolutional Networkscited by 1,165
  12. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
38 more
  1. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  2. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  3. 2020Directional Message Passing for Molecular Graphscited by 561
  4. 2020Hopfield Networks is All You Needcited by 475
  5. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  6. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  7. 2018Spherical CNNscited by 456
  8. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
  9. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 403
  10. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  11. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 255
  12. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 242
  13. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 237
  14. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 168
  15. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 159
  16. 2019Relational Pooling for Graph Representationscited by 150
  17. 2018Generating 3D Adversarial Point Cloudscited by 144
  18. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  19. 2018Universal approximations of invariant maps by neural networkscited by 127
  20. 2020Lorentz Group Equivariant Neural Network for Particle Physicscited by 121
  21. 2020Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Reviewcited by 116
  22. 2018PointCloud Saliency Mapscited by 112
  23. 2020Certified Robustness to Label-Flipping Attacks via Randomized Smoothingcited by 108
  24. 2018Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputscited by 98
  25. 2017Maximum Resilience of Artificial Neural Networkscited by 97
  26. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  27. 2021A comprehensive survey on point cloud registrationcited by 84
  28. 2020On Certifying Robustness against Backdoor Attacks via Randomized Smoothingcited by 77
  29. 2014Differential Privacy and Machine Learning: a Survey and Reviewcited by 67
  30. 2019Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifierscited by 65
  31. 2019Adversarial Attack and Defense on Point Setscited by 63
  32. 2019Adversarial Objects Against LiDAR-Based Autonomous Driving Systemscited by 63
  33. 2019Certifiable Robustness and Robust Training for Graph Convolutional Networkscited by 59
  34. 2020Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and Morecited by 56
  35. 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
  36. 2020Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbationscited by 55
  37. 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
  38. 2019Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothingcited by 54

50 most cited of 83 All 83 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 4.

7 papers.

  1. 2023Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networkscited by 10
  2. 2023Hierarchical Randomized Smoothingcited by 9
  3. 2025Effective Data Pruning through Score Extrapolationcited by 2
  4. 2025Reconcile Certified Robustness and Accuracy for DNN-based Smoothed Majority Vote Classifiercited by 2
  5. 2024Integrating uncertainty quantification into randomized smoothing based robustness guaranteescited by 1
  6. 2025Adversarial Examples in Environment Perception for Automated Driving (Review)cited by 1
  7. 2025Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifierscited by 0