mlsanityData to 7 Oct 2026

Jacobian Adversarially Regularized Networks for Robustness

arXiv 1912.10185 ↗First posted 21 Dec 2019cs.CV cs.CR cs.NEcited by 40

Not on the map. Why?

Abstract (arXiv)

Adversarial examples are crafted with imperceptible perturbations with the intent to fool neural networks. Against such attacks, adversarial training and its variants stand as the strongest defense to date. Previous studies have pointed out that robust models that have undergone adversarial training tend to produce more salient and interpretable Jacobian matrices than their non-robust counterparts. A natural question is whether a model trained with an objective to produce salient Jacobian can result in better robustness. This paper answers this question with affirmative empirical results. We propose Jacobian Adversarially Regularized Networks (JARN) as a method to optimize the saliency of a classifier's Jacobian by adversarially regularizing the model's Jacobian to resemble natural training images. Image classifiers trained with JARN show improved robust accuracy compared to standard models on the MNIST, SVHN and CIFAR-10 datasets, uncovering a new angle to boost robustness without using adversarial training examples.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 14; 2023: 10; 2024: 3; 2025: 3; 2026: 3.

40 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2021Fair Mixup: Fairness via Interpolationcited by 109
  3. 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 109
  4. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  5. 2023Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferabilitycited by 32
  6. 2021Attacking Adversarial Attacks as A Defensecited by 31
  7. 2023Improving Generalization of Adversarial Training via Robust Critical Fine-Tuningcited by 23
  8. 2023Adversarial Training Should Be Cast as a Non-Zero-Sum Gamecited by 13
  9. 2024Gradient-Regularized Out-of-Distribution Detectioncited by 13
  10. 2022How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?cited by 11
  11. 2023Certified Zeroth-order Black-Box Defense with Robust UNet Denoisercited by 11
  12. 2023Exact Count of Boundary Pieces of ReLU Classifiers: Towards the Proper Complexity Measure for Classificationcited by 11
28 more
  1. 2021Improving Model Robustness with Latent Distribution Locally and Globallycited by 9
  2. 2021Impact of Spatial Frequency Based Constraints on Adversarial Robustnesscited by 8
  3. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 8
  4. 2024Machine Learning Robustness: A Primercited by 8
  5. 2022A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challengescited by 7
  6. 2023Towards Robust and Accurate Visual Promptingcited by 5
  7. 2021Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approachcited by 4
  8. 2022Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detectioncited by 3
  9. 2022Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) frameworkcited by 2
  10. 2022Training-Free Robust Multimodal Learning via Sample-Wise Jacobian Regularizationcited by 2
  11. 2022Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defensecited by 2
  12. 2022Data-free Defense of Black Box Models Against Adversarial Attackscited by 2
  13. 2025GrokAlign: Geometric Characterisation and Acceleration of Grokkingcited by 2
  14. 2022Bandwidth Selection for Gaussian Kernel Ridge Regression via Jacobian Controlcited by 1
  15. 2022DE-CROP: Data-efficient Certified Robustness for Pretrained Classifierscited by 1
  16. 2023Fourier Sensitivity and Regularization of Computer Vision Modelscited by 1
  17. 2023IRAD: Implicit Representation-driven Image Resampling against Adversarial Attackscited by 1
  18. 2024Adversarially robust generalization theory via Jacobian regularization for deep neural networkscited by 1
  19. 2025Adversarial Examples in Environment Perception for Automated Driving (Review)cited by 1
  20. 2021Noise Modulation: Let Your Model Interpret Itselfcited by 0
  21. 2022DAD: Data-free Adversarial Defense at Test Timecited by 0
  22. 2022Robust Few-shot Learning Without Using any Adversarial Samplescited by 0
  23. 2023DAD++: Improved Data-free Test Time Adversarial Defensecited by 0
  24. 2023Training Image Derivatives: Increased Accuracy and Universal Robustnesscited by 0
  25. 2025Exploring Visual Prompting: Robustness Inheritance and Beyondcited by 0
  26. 2026Quadratic Upper Bound for Boosting Robustnesscited by 0
  27. 2026On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspacescited by 0
  28. 2026Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performancecited by 0