mlsanityData to 14 Oct 2026

Parseval Networks: Improving Robustness to Adversarial Examples

arXiv 1704.08847 ↗First posted 28 Apr 2017stat.ML cs.AI cs.CRcited by 293

Not on the map. Why?

Abstract (arXiv)

We introduce Parseval networks, a form of deep neural networks in which the Lipschitz constant of linear, convolutional and aggregation layers is constrained to be smaller than 1. Parseval networks are empirically and theoretically motivated by an analysis of the robustness of the predictions made by deep neural networks when their input is subject to an adversarial perturbation. The most important feature of Parseval networks is to maintain weight matrices of linear and convolutional layers to be (approximately) Parseval tight frames, which are extensions of orthogonal matrices to non-square matrices. We describe how these constraints can be maintained efficiently during SGD. We show that Parseval networks match the state-of-the-art in terms of accuracy on CIFAR-10/100 and Street View House Numbers (SVHN) while being more robust than their vanilla counterpart against adversarial examples. Incidentally, Parseval networks also tend to train faster and make a better usage of the full capacity of the networks.

Key facts. Cited by 293 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 75; 2022: 52; 2023: 42; 2024: 36; 2025: 40; 2026: 46.

293 papers.

Sort:

By area:

  1. 2021Spatial-Temporal Graph ODE Networks for Traffic Flow Forecastingcited by 210
  2. 2021Trustworthy AI: From Principles to Practicescited by 207
  3. 2025Training Deep Learning Models with Norm-Constrained LMOscited by 192
  4. 2021A Universal Law of Robustness via Isoperimetrycited by 151
  5. 2021On the Convergence and Robustness of Adversarial Trainingcited by 130
  6. 2021Globally-Robust Neural Networkscited by 108
  7. 2021Orthogonalizing Convolutional Layers with the Cayley Transformcited by 105
  8. 2022Neural Collapse: A Review on Modelling Principles and Generalizationcited by 95
  9. 2021JFB: Jacobian-Free Backpropagation for Implicit Networkscited by 86
  10. 2022Learning Smooth Neural Functions via Lipschitz Regularizationcited by 86
  11. 2021RobustART: Benchmarking Robustness on Architecture Design and Training Techniquescited by 79
  12. 2021Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networkscited by 74
38 more
  1. 2022PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Latticescited by 73
  2. 2021Skew Orthogonal Convolutionscited by 67
  3. 2021Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspectivecited by 65
  4. 2021Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Boundscited by 65
  5. 2021A Dynamical System Perspective for Lipschitz Neural Networkscited by 60
  6. 2021Human-Adversarial Visual Question Answeringcited by 57
  7. 2021Exploring Memorization in Adversarial Trainingcited by 55
  8. 2022Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspectivecited by 51
  9. 2021Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100cited by 47
  10. 2021A Deep Value-network Based Approach for Multi-Driver Order Dispatchingcited by 45
  11. 2023How Smooth Is Attention?cited by 44
  12. 2022Make Some Noise: Reliable and Efficient Single-Step Adversarial Trainingcited by 43
  13. 2021A Comprehensive Evaluation Framework for Deep Model Robustnesscited by 42
  14. 2021Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neuronscited by 40
  15. 2022Regret Minimization with Performative Feedbackcited by 40
  16. 2022Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networkscited by 39
  17. 2022On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learningcited by 39
  18. 2021Rethinking Graph Auto-Encoder Models for Attributed Graph Clusteringcited by 37
  19. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  20. 2022LOT: Layer-wise Orthogonal Training on Improving ℓ2 Certified Robustnesscited by 33
  21. 2023On the Stability of Expressive Positional Encodings for Graphscited by 33
  22. 2024CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularizationcited by 33
  23. 2021Attacking Adversarial Attacks as A Defensecited by 32
  24. 2021Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defensescited by 30
  25. 2021Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networkscited by 30
  26. 2021Combating Adversaries with Anti-Adversariescited by 27
  27. 2023Some Fundamental Aspects about Lipschitz Continuity of Neural Networkscited by 26
  28. 2021Boosting the Certified Robustness of L-infinity Distance Netscited by 24
  29. 2022Improving Lipschitz-Constrained Neural Networks by Learning Activation Functionscited by 24
  30. 2024Plasticity Loss in Deep Reinforcement Learning: A Surveycited by 24
  31. 2022Robustness Implies Generalization via Data-Dependent Generalization Boundscited by 23
  32. 2022Approximation bounds for norm constrained neural networks with applications to regression and GANscited by 22
  33. 2025Softmax is 1/2-Lipschitz: A tight bound across all ℓp normscited by 22
  34. 2025SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMscited by 22
  35. 2021CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selectioncited by 21
  36. 2023Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularizationcited by 21
  37. 2024Parseval Regularization for Continual Reinforcement Learningcited by 21
  38. 2025Training Transformers with Enforced Lipschitz Constantscited by 20

50 most cited of 293 All 293 (JSON)