mlsanityData to 14 Oct 2026

Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss

arXiv 2505.15174 ↗First posted 21 May 2025cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Lipschitz neural networks are well-known for providing certified robustness in deep learning. In this paper, we present a novel, efficient Block Reflector Orthogonal (BRO) layer that enhances the capability of orthogonal layers on constructing more expressive Lipschitz neural architectures. In addition, by theoretically analyzing the nature of Lipschitz neural networks, we introduce a new loss function that employs an annealing mechanism to increase margin for most data points. This enables Lipschitz models to provide better certified robustness. By employing our BRO layer and loss function, we design BRONet - a simple yet effective Lipschitz neural network that achieves state-of-the-art certified robustness. Extensive experiments and empirical analysis on CIFAR-10/100, Tiny-ImageNet, and ImageNet validate that our method outperforms existing baselines. The implementation is available at https://github.com/ntuaislab/BRONet.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 53 of its 71 references that are in the map. First posted on arXiv 21 May 2025.

Builds on

53 of 71 references.

References · 53

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  9. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  10. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  11. 2017Spectrally-normalized margin bounds for neural networkscited by 686
  12. 2019Adversarial Training for Free!cited by 643
38 more
  1. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  2. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 415
  3. 2023Analyzing and Improving the Training Dynamics of Diffusion Modelscited by 402
  4. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  5. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 336
  6. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
  7. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 299
  8. 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 293
  9. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  10. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 242
  11. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 228
  12. 2018Sorting out Lipschitz function approximationcited by 213
  13. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 208
  14. 2018Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networkscited by 195
  15. 2018Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networkscited by 176
  16. 2020Randomized Smoothing of All Shapes and Sizescited by 147
  17. 2021Globally-Robust Neural Networkscited by 108
  18. 2021Orthogonalizing Convolutional Layers with the Cayley Transformcited by 105
  19. 2022General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcited by 103
  20. 2019Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networkscited by 87
  21. 2018Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compressioncited by 74
  22. 2018Generalizable Adversarial Training via Spectral Normalizationcited by 68
  23. 2021Skew Orthogonal Convolutionscited by 67
  24. 2023Robust Evaluation of Diffusion-Based Adversarial Purificationcited by 65
  25. 2021A Dynamical System Perspective for Lipschitz Neural Networkscited by 60
  26. 2023A Unified Algebraic Perspective on Lipschitz Neural Networkscited by 60
  27. 2022Certified Training: Small Boxes are All You Needcited by 52
  28. 2023Direct Parameterization of Lipschitz-Bounded Deep Networkscited by 51
  29. 2021Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100cited by 47
  30. 2022Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagationcited by 45
  31. 2020Deep Isometric Learning for Visual Recognitioncited by 39
  32. 2022Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networkscited by 39
  33. 2018Evaluating and Understanding the Robustness of Adversarial Logit Pairingcited by 34
  34. 2022LOT: Layer-wise Orthogonal Training on Improving ℓ2 Certified Robustnesscited by 33
  35. 2021Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networkscited by 30
  36. 2016Norm-preserving Orthogonal Permutation Linear Unit Activation Functions (OPLU)cited by 16
  37. 2021Existence, Stability and Scalability of Orthogonal Convolutional Neural Networkscited by 16
  38. 20231-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustnesscited by 16

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026LipNeXt: Scaling up Lipschitz-based Certified Robustness to Billion-parameter Modelscited by 2
  2. 2026On the Extreme Variance of Certified Local Robustness Across Model Seedscited by 0
  3. 2026Expanding the Role of Diffusion Models for Robust Classifier Trainingcited by 0
  4. 2026Demystifying Lipschitz verification: positive matrices, negative resultscited by 0
  5. 2026LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networkscited by 0