mlsanityData to 7 Oct 2026

Towards Out-of-Distribution Adversarial Robustness

arXiv 2210.03150 ↗First posted 6 Oct 2022cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Adversarial robustness continues to be a major challenge for deep learning. A core issue is that robustness to one type of attack often fails to transfer to other attacks. While prior work establishes a theoretical trade-off in robustness against different Lp norms, we show that there is potential for improvement against many commonly used attacks by adopting a domain generalisation approach. Concretely, we treat each type of attack as a domain, and apply the Risk Extrapolation method (REx), which promotes similar levels of robustness against all training attacks. Compared to existing methods, we obtain similar or superior worst-case adversarial robustness on attacks seen during training. Moreover, we achieve superior performance on families or tunings of attacks only encountered at test time. On ensembles of attacks, our approach improves the accuracy from 3.4% with the best existing baseline to 25.9% on MNIST, and from 16.9% to 23.5% on CIFAR10.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 38 of its 51 references that are in the map. First posted on arXiv 6 Oct 2022.

Builds on

38 of 51 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  9. 2019Invariant Risk Minimizationcited by 1,832
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  12. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
26 more
  1. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  2. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  3. 2020In Search of Lost Domain Generalizationcited by 1,042
  4. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  5. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  6. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  7. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  8. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  9. 2020Overfitting in adversarially robust deep learningcited by 504
  10. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  11. 2020Bag of Tricks for Adversarial Trainingcited by 199
  12. 2018Spatially Transformed Adversarial Examplescited by 195
  13. 2020Invariant Risk Minimization Gamescited by 188
  14. 2019Adversarial Training and Robustness for Multiple Perturbationscited by 182
  15. 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
  16. 2022Revisiting Weakly Supervised Pre-Training of Visual Perception Modelscited by 116
  17. 2019Adversarial Robustness Against the Union of Multiple Perturbation Modelscited by 88
  18. 2019Functional Adversarial Attackscited by 82
  19. 2020Secure and Robust Machine Learning for Healthcare: A Surveycited by 77
  20. 2019advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorchcited by 69
  21. 2020An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Modelscited by 67
  22. 2018Improving the Generalization of Adversarial Training with Domain Adaptationcited by 48
  23. 2018On the Geometry of Adversarial Examplescited by 43
  24. 2019Accurate, reliable and fast robustness evaluationcited by 43
  25. 2019A Research Agenda: Dynamic Models to Defend Against Correlated Attackscited by 18
  26. 2020Adversarial Feature Desensitizationcited by 12

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 0; 2025: 1.

5 papers.

  1. 2023Adversarial Attacks on Foundational Vision Modelscited by 13
  2. 2023OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shiftcited by 4
  3. 2023Expecting The Unexpected: Towards Broad Out-Of-Distribution Detectioncited by 3
  4. 2025A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategycited by 1
  5. 2023Adversarial defense based on distribution transfercited by 0