mlsanityData to 7 Oct 2026

Accelerated Smoothing: A Scalable Approach to Randomized Smoothing

arXiv 2402.07498 ↗First posted 12 Feb 2024cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Randomized smoothing has emerged as a potent certifiable defense against adversarial attacks by employing smoothing noises from specific distributions to ensure the robustness of a smoothed classifier. However, the utilization of Monte Carlo sampling in this process introduces a compute-intensive element, which constrains the practicality of randomized smoothing on a larger scale. To address this limitation, we propose a novel approach that replaces Monte Carlo sampling with the training of a surrogate neural network. Through extensive experimentation in various settings, we demonstrate the efficacy of our approach in approximating the smoothed classifier with remarkable precision. Furthermore, we demonstrate that our approach significantly accelerates the robust radius certification process, providing nearly 600X improvement in computation time, overcoming the computational bottlenecks associated with traditional randomized smoothing.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 39 references that are in the map. First posted on arXiv 12 Feb 2024.

Builds on

33 of 39 references.

References · 33

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2016Adversarial examples in the physical worldcited by 1,762
  5. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  6. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  8. 2018Robustness May Be at Odds with Accuracycited by 873
  9. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  10. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  11. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  12. 2017Countering Adversarial Images using Input Transformationscited by 517
21 more
  1. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  2. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  3. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  4. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
  5. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  6. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  7. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 204
  8. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  9. 2020Randomized Smoothing of All Shapes and Sizescited by 146
  10. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  11. 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
  12. 2020(De)Randomized Smoothing for Certifiable Defense against Patch Attackscited by 97
  13. 2020Consistency Regularization for Certified Robustness of Smoothed Classifierscited by 73
  14. 2019Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothingcited by 54
  15. 2020Certified Defense to Image Transformations via Randomized Smoothingcited by 51
  16. 2020TSS: Transformation-Specific Smoothing for Robustness Certificationcited by 49
  17. 2021SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustnesscited by 49
  18. 2020Random Smoothing Might be Unable to Certify ℓ_∞ Robustness for High-Dimensional Imagescited by 35
  19. 2022Double Sampling Randomized Smoothingcited by 22
  20. 2020Adversarial robustness via robust low rank representationscited by 14
  21. 2021Input-Specific Robustness Certification for Randomized Smoothingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026RRISE: Robust Radius Inference via a Surrogate Estimatorcited by 0