mlsanityData to 7 Oct 2026

Scaleable input gradient regularization for adversarial robustness

arXiv 1905.11468 ↗First posted 27 May 2019stat.ML cs.CR cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

In this work we revisit gradient regularization for adversarial robustness with some new ingredients. First, we derive new per-image theoretical robustness bounds based on local gradient information. These bounds strongly motivate input gradient regularization. Second, we implement a scaleable version of input gradient regularization which avoids double backpropagation: adversarially robust ImageNet models are trained in 33 hours on four consumer grade GPUs. Finally, we show experimentally and through theoretical certification that input gradient regularization is competitive with adversarial training. Moreover we demonstrate that gradient regularization does not lead to gradient obfuscation or gradient masking.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 9; 2023: 6; 2024: 12; 2025: 6; 2026: 2.

45 papers.

Sort:

By area:

  1. 2021Gradient-enhanced physics-informed neural networks for forward and inverse PDE problemscited by 220
  2. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  3. 2021Globally-Robust Neural Networkscited by 106
  4. 2025Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyondcited by 76
  5. 2024H-Consistency Guarantees for Regressioncited by 21
  6. 2021The Geometry of Adversarial Training in Binary Classificationcited by 20
  7. 2022Adversarial Rademacher Complexity of Deep Neural Networkscited by 18
  8. 2023Adversarial robustness of amortized Bayesian inferencecited by 17
  9. 2024Understanding polysemanticity in neural networks through coding theorycited by 17
  10. 2022Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Biascited by 16
  11. 2022Do Perceptually Aligned Gradients Imply Adversarial Robustness?cited by 15
  12. 2021Learning Security Classifiers with Verified Global Robustness Propertiescited by 14
33 more
  1. 2022Zeroth-Order Alternating Gradient Descent Ascent Algorithms for a Class of Nonconvex-Nonconcave Minimax Problemscited by 10
  2. 2022Gamma-convergence of a nonlocal perimeter arising in adversarial machine learningcited by 10
  3. 2024PAC-Bayes-Chernoff bounds for unbounded lossescited by 9
  4. 2024Enhancing Adversarial Robustness in SNNs with Sparse Gradientscited by 9
  5. 2021On the regularized risk of distributionally robust learning over deep neural networkscited by 8
  6. 2023Nash Equilibria, Regularization and Computation in Optimal Transport-Based Distributionally Robust Optimizationcited by 8
  7. 2021Derivative-free Alternating Projection Algorithms for General Nonconvex-Concave Minimax Problemscited by 7
  8. 2024Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularizationcited by 7
  9. 2022Tikhonov Regularization is Optimal Transport Robust under Martingale Constraintscited by 6
  10. 2024Characterizing Model Robustness via Natural Input Gradientscited by 6
  11. 2023On adversarial robustness and the use of Wasserstein ascent-descent dynamics to enforce itcited by 4
  12. 2025Robustness questions the interpretability of graph neural networks: what to do?cited by 4
  13. 2024MIRACLE3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model Constructioncited by 3
  14. 2024TAEN: A Model-Constrained Tikhonov Autoencoder Network for Forward and Inverse Problemscited by 3
  15. 2023A Practical Upper Bound for the Worst-Case Attribution Deviationscited by 2
  16. 2024Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Processcited by 2
  17. 2024Minimax rates of convergence for nonparametric regression under adversarial attackscited by 2
  18. 2021Dynamic Efficient Adversarial Training Guided by Gradient Magnitudecited by 1
  19. 2021Dual Head Adversarial Trainingcited by 1
  20. 2022Enhancing Classifier Conservativeness and Robustness by Polynomialitycited by 1
  21. 2022Gradient Obfuscation Checklist Test Gives a False Sense of Securitycited by 1
  22. 2023Can Adversarial Examples Be Parsed to Reveal Victim Model Information?cited by 1
  23. 2024Is Adversarial Training with Compressed Datasets Effective?cited by 1
  24. 2024Do Counterfactual Examples Complicate Adversarial Training?cited by 1
  25. 2025A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challengescited by 1
  26. 2021An Interpretable Neural Network for Parameter Inferencecited by 0
  27. 2021Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layerscited by 0
  28. 2023Releasing Inequality Phenomenon in ℓ∞-norm Adversarial Training via Input Gradient Distillationcited by 0
  29. 2025Towards Understanding the Optimization Mechanisms in Deep Learningcited by 0
  30. 2025Framework GNN-AID: Graph Neural Network Analysis Interpretation and Defensecited by 0
  31. 2025DReS: Dual Reconstruction Smoothing for Functional Regularizationcited by 0
  32. 2026Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillationcited by 0
  33. 2026Dynamics to decision: A mathematical theory of Lyapunov spectra and decision boundaries in deep classifierscited by 0