mlsanityData to 14 Oct 2026

Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification

arXiv 2205.09619 ↗First posted 19 May 2022cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to either real-world distribution shifts (e.g., common corruptions and perturbations, spatial transformations, and natural adversarial examples) or worst-case distribution shifts (e.g., optimized adversarial examples). In this work, we propose the Decision Region Quantification (DRQ) algorithm to improve the robustness of any differentiable pre-trained model against both real-world and worst-case distribution shifts in the data. DRQ analyzes the robustness of local decision regions in the vicinity of a given data point to make more reliable predictions. We theoretically motivate the DRQ algorithm by showing that it effectively smooths spurious local extrema in the decision surface. Furthermore, we propose an implementation using targeted and untargeted adversarial attacks. An extensive empirical evaluation shows that DRQ increases the robustness of adversarially and non-adversarially trained models against real-world and worst-case distribution shifts on several computer vision benchmark datasets.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 19 May 2022.

Builds on

32 of 44 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  7. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  8. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  10. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  11. 2019Natural Adversarial Examplescited by 1,408
  12. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
20 more
  1. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  2. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  3. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  4. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  5. 2020Overfitting in adversarially robust deep learningcited by 506
  6. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 431
  7. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 377
  8. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  9. 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
  10. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  11. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  12. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 278
  13. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 204
  14. 2020Understanding and Mitigating the Tradeoff Between Robustness and Accuracycited by 149
  15. 2021Adversarial purification with Score-based generative modelscited by 134
  16. 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
  17. 2017Synthesizing Robust Adversarial Examplescited by 39
  18. 2021Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attackscited by 33
  19. 2021CLIP: Cheap Lipschitz Training of Neural Networkscited by 29
  20. 2021Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysiscited by 13

Built on by

Cited by year

Citing papers per year: 2023: 6; 2024: 4; 2025: 6.

16 papers.

Sort:

By area:

  1. 2024Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Spacecited by 91
  2. 2023Robust Classification via a Single Diffusion Modelcited by 79
  3. 2023Adversarial Attacks and Defenses in Large Language Models: Old and New Threatscited by 49
  4. 2023How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?cited by 14
  5. 2025Robustness and Cybersecurity in the EU Artificial Intelligence Actcited by 11
  6. 2025When to retrain a machine learning modelcited by 8
  7. 2023Raising the Bar for Certified Adversarial Robustness with Diffusion Modelscited by 7
  8. 2024Efficient Time Series Processing for Transformers and State-Space Models through Token Mergingcited by 7
  9. 2025Joint Out-of-Distribution Filtering and Data Discovery Active Learningcited by 7
  10. 2023Class-Conditioned Transformation for Enhanced Robust Image Classificationcited by 5
  11. 2025Byte Pair Encoding for Efficient Time Series Forecastingcited by 5
  12. 2023It begins with a boundary: A geometric view on probabilistically robust learningcited by 3
4 more
  1. 2024Towards Stable Machine Learning Model Retraining via Slowly Varying Sequencescited by 2
  2. 2025Effective Data Pruning through Score Extrapolationcited by 2
  3. 2024Quantile Activation: Correcting a Failure Mode of ML Modelscited by 1
  4. 2025The Challenger: When Do New Data Sources Justify Switching Machine Learning Models?cited by 0