mlsanityData to 7 Oct 2026

General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothing

arXiv 2309.16710 ↗First posted 17 Aug 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Randomized smoothing is the state-of-the-art approach to construct image classifiers that are provably robust against additive adversarial perturbations of bounded magnitude. However, it is more complicated to construct reasonable certificates against semantic transformation (e.g., image blurring, translation, gamma correction) and their compositions. In this work, we propose General Lipschitz (GL), a new framework to certify neural networks against composable resolvable semantic perturbations. Within the framework, we analyze transformation-dependent Lipschitz-continuity of smoothed classifiers w.r.t. transformation parameters and derive corresponding robustness certificates. Our method performs comparably to state-of-the-art approaches on the ImageNet dataset.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 69 of its 86 references that are in the map. First posted on arXiv 17 Aug 2023.

Builds on

69 of 86 references.

References · 69

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  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. 2016Adversarial examples in the physical worldcited by 1,762
  9. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  11. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  12. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
38 more
  1. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  2. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  3. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  4. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  5. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  6. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  7. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  8. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
  9. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  10. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 311
  11. 2018Adversarial Attacks and Defences: A Surveycited by 259
  12. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  13. 2019Simple Black-box Adversarial Attackscited by 249
  14. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  15. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  16. 2018Sorting out Lipschitz function approximationcited by 211
  17. 2018Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networkscited by 193
  18. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  19. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 161
  20. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  21. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  22. 2020Randomized Smoothing of All Shapes and Sizescited by 146
  23. 2018Scaling provable adversarial defensescited by 141
  24. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  25. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  26. 2020SoK: Certified Robustness for Deep Neural Networkscited by 100
  27. 2017Maximum Resilience of Artificial Neural Networkscited by 97
  28. 2017Universal Adversarial Perturbations Against Semantic Image Segmentationcited by 92
  29. 2018Semantic Adversarial Examplescited by 86
  30. 2017A General Framework for Adversarial Examples with Objectivescited by 82
  31. 2020Consistency Regularization for Certified Robustness of Smoothed Classifierscited by 73
  32. 2019Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifierscited by 56
  33. 2020Certified Defense to Image Transformations via Randomized Smoothingcited by 51
  34. 2020TSS: Transformation-Specific Smoothing for Robustness Certificationcited by 49
  35. 2022Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspectivecited by 48
  36. 2021Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Drivingcited by 45
  37. 2020Probabilistic Safety for Bayesian Neural Networkscited by 41
  38. 2020Second-Order Provable Defenses against Adversarial Attackscited by 39

50 most cited of 69 All 69 (JSON)

Built on by

Not cited yet.