mlsanityData to 14 Oct 2026

Transfer of Adversarial Robustness Between Perturbation Types

arXiv 1905.01034 ↗First posted 3 May 2019cs.LG cs.AI cs.CRcited by 25

Not on the map. Why?

Abstract (arXiv)

We study the transfer of adversarial robustness of deep neural networks between different perturbation types. While most work on adversarial examples has focused on L_∞ and L2-bounded perturbations, these do not capture all types of perturbations available to an adversary. The present work evaluates 32 attacks of 5 different types against models adversarially trained on a 100-class subset of ImageNet. Our empirical results suggest that evaluating on a wide range of perturbation sizes is necessary to understand whether adversarial robustness transfers between perturbation types. We further demonstrate that robustness against one perturbation type may not always imply and may sometimes hurt robustness against other perturbation types. In light of these results, we recommend evaluation of adversarial defenses take place on a diverse range of perturbation types and sizes.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). First posted on arXiv 3 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 4; 2023: 7; 2024: 5; 2025: 2; 2026: 2.

25 papers.

Sort:

By area:

  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  2. 2021On the effectiveness of adversarial training against common corruptionscited by 71
  3. 2023Towards quantum enhanced adversarial robustness in machine learningcited by 28
  4. 2021Adversarial Robustness against Multiple and Single lp-Threat Models via Quick Fine-Tuning of Robust Classifierscited by 23
  5. 2025X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIPcited by 21
  6. 2024Estimating the Probabilities of Rare Outputs in Language Modelscited by 16
  7. 2022Why adversarial training can hurt robust accuracycited by 14
  8. 2021Real-time Detection of Practical Universal Adversarial Perturbationscited by 6
  9. 2022On the interplay of adversarial robustness and architecture components: patches, convolution and attentioncited by 4
  10. 2023Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networkscited by 4
  11. 2022Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challengescited by 3
  12. 2023Regret-Based Defense in Adversarial Reinforcement Learningcited by 3
13 more
  1. 2025Achievable distributional robustness when the robust risk is only partially identifiedcited by 3
  2. 2024A Modified Depolarization Approach for Efficient Quantum Machine Learningcited by 2
  3. 2024On Minimizing Adversarial Counterfactual Error in Adversarial RLcited by 2
  4. 2024RAMP: Boosting Adversarial Robustness Against Multiple lp Perturbations for Universal Robustnesscited by 1
  5. 2024Towards Generalized Certified Robustness with Multi-Norm Trainingcited by 1
  6. 2026Estimating Rare Events in Language Models with Proper Evaluationcited by 1
  7. 2021Robustifying ℓ_∞ Adversarial Training to the Union of Perturbation Modelscited by 0
  8. 2022Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answeringcited by 0
  9. 2023Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneckcited by 0
  10. 2023Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgetscited by 0
  11. 2023Parameter-Saving Adversarial Training: Reinforcing Multi-Perturbation Robustness via Hypernetworkscited by 0
  12. 2023On Continuity of Robust and Accurate Classifierscited by 0
  13. 2026Adversarial Robustness of Deep Learning-Based Thyroid Nodule Segmentation in Ultrasoundcited by 0