mlsanityData to 7 Oct 2026

Towards Strong Certified Defense with Universal Asymmetric Randomization

arXiv 2510.19977 ↗First posted 22 Oct 2025cs.LG cs.CRcited by 1

Not on the map. Why?

Abstract (arXiv)

Randomized smoothing has become essential for achieving certified adversarial robustness in machine learning models. However, current methods primarily use isotropic noise distributions that are uniform across all data dimensions, such as image pixels, limiting the effectiveness of robustness certification by ignoring the heterogeneity of inputs and data dimensions. To address this limitation, we propose UCAN: a novel technique that underlineUniversally underlineCertifies adversarial robustness with underlineAnisotropic underlineNoise. UCAN is designed to enhance any existing randomized smoothing method, transforming it from symmetric (isotropic) to asymmetric (anisotropic) noise distributions, thereby offering a more tailored defense against adversarial attacks. Our theoretical framework is versatile, supporting a wide array of noise distributions for certified robustness in different ℓp-norms and applicable to any arbitrary classifier by guaranteeing the classifier's prediction over perturbed inputs with provable robustness bounds through tailored noise injection. Additionally, we develop a novel framework equipped with three exemplary noise parameter generators (NPGs) to optimally fine-tune the anisotropic noise parameters for different data dimensions, allowing for pursuing different levels of robustness enhancements in practice.Empirical evaluations underscore the significant leap in UCAN's performance over existing state-of-the-art methods, demonstrating up to 182.6% improvement in certified accuracy at large certified radii on MNIST, CIFAR10, and ImageNet datasets.footnoteCode is anonymously available at hrefhttps://github.com/youbin2014/UCAN/https://github.com/youbin2014/UCAN/

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 53 of its 75 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

53 of 75 references.

References · 53

  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. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  11. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  12. 2019Adversarial Training for Free!cited by 638
38 more
  1. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  2. 2017Generative Adversarial Networks: An Overviewcited by 588
  3. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  4. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  5. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  6. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  7. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  8. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  9. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  10. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
  11. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  12. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  13. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 311
  14. 2018Certified Defenses against Adversarial Examplescited by 305
  15. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  16. 2016Safety Verification of Deep Neural Networkscited by 262
  17. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  18. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
  19. 2018Sorting out Lipschitz function approximationcited by 211
  20. 2018Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networkscited by 193
  21. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  22. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  23. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  24. 2020Randomized Smoothing of All Shapes and Sizescited by 146
  25. 2018Scaling provable adversarial defensescited by 141
  26. 2017An approach to reachability analysis for feed-forward ReLU neural networkscited by 126
  27. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  28. 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
  29. 2017Maximum Resilience of Artificial Neural Networkscited by 97
  30. 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
  31. 2020Consistency Regularization for Certified Robustness of Smoothed Classifierscited by 73
  32. 2019Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifierscited by 65
  33. 2021SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustnesscited by 49
  34. 2021Boosting Randomized Smoothing with Variance Reduced Classifierscited by 47
  35. 2020Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Frameworkcited by 45
  36. 2021On the Certified Robustness for Ensemble Models and Beyondcited by 40
  37. 2020Data-Dependent Randomized Smoothingcited by 37
  38. 2021Intriguing Properties of Input-dependent Randomized Smoothingcited by 24

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Laplace-Bridged Randomized Smoothing for Fast Certified Robustnesscited by 0