mlsanityData to 7 Oct 2026

Generalizability of Adversarial Robustness Under Distribution Shifts

arXiv 2209.15042 ↗First posted 29 Sep 2022cs.LG cs.AI cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent progress in empirical and certified robustness promises to deliver reliable and deployable Deep Neural Networks (DNNs). Despite that success, most existing evaluations of DNN robustness have been done on images sampled from the same distribution on which the model was trained. However, in the real world, DNNs may be deployed in dynamic environments that exhibit significant distribution shifts. In this work, we take a first step towards thoroughly investigating the interplay between empirical and certified adversarial robustness on one hand and domain generalization on another. To do so, we train robust models on multiple domains and evaluate their accuracy and robustness on an unseen domain. We observe that: (1) both empirical and certified robustness generalize to unseen domains, and (2) the level of generalizability does not correlate well with input visual similarity, measured by the FID between source and target domains. We also extend our study to cover a real-world medical application, in which adversarial augmentation significantly boosts the generalization of robustness with minimal effect on clean data accuracy.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 55 of its 80 references that are in the map. First posted on arXiv 29 Sep 2022.

Builds on

55 of 80 references.

References · 55

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  10. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  11. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  12. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
38 more
  1. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  2. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  3. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  4. 2020In Search of Lost Domain Generalizationcited by 1,042
  5. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  6. 2018Robustness May Be at Odds with Accuracycited by 873
  7. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  8. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  9. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  10. 2021Domain Generalization: A Surveycited by 760
  11. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  12. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  13. 2021Domain Generalization with MixStylecited by 563
  14. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  15. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  16. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  17. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
  18. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  19. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  20. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  21. 2018Certified Defenses against Adversarial Examplescited by 305
  22. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  23. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
  24. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  25. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  26. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  27. 2021Partial success in closing the gap between human and machine visioncited by 185
  28. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
  29. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  30. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  31. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  32. 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
  33. 2020Deep Visual Domain Adaptationcited by 91
  34. 2018How good is my GAN?cited by 74
  35. 2019Adversarially robust transfer learningcited by 66
  36. 2021Domain Invariant Representation Learning with Domain Density Transformationscited by 53
  37. 2020Data-Dependent Randomized Smoothingcited by 37
  38. 2021Adversarial Training Helps Transfer Learning via Better Representationscited by 36

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 1; 2026: 1.

6 papers.

  1. 2024What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?cited by 6
  2. 2023OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shiftcited by 4
  3. 2024Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectorscited by 2
  4. 2024RAMP: Boosting Adversarial Robustness Against Multiple lp Perturbations for Universal Robustnesscited by 1
  5. 2025Adversarial Training Improves Generalization Under Distribution Shifts in Bird Sound Classificationcited by 0
  6. 2026Learning Robustness at Test-Time from a Non-Robust Teachercited by 0