mlsanityData to 7 Oct 2026

Provably Safeguarding a Classifier from OOD and Adversarial Samples: an Extreme Value Theory Approach

arXiv 2501.10202 ↗First posted 17 Jan 2025stat.ML cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper introduces a novel method, Sample-efficient Probabilistic Detection using Extreme Value Theory (SPADE), which transforms a classifier into an abstaining classifier, offering provable protection against out-of-distribution and adversarial samples. The approach is based on a Generalized Extreme Value (GEV) model of the training distribution in the classifier's latent space, enabling the formal characterization of OOD samples. Interestingly, under mild assumptions, the GEV model also allows for formally characterizing adversarial samples. The abstaining classifier, which rejects samples based on their assessment by the GEV model, provably avoids OOD and adversarial samples. The empirical validation of the approach, conducted on various neural architectures (ResNet, VGG, and Vision Transformer) and medium and large-sized datasets (CIFAR-10, CIFAR-100, and ImageNet), demonstrates its frugality, stability, and efficiency compared to the state of the art.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 46 of its 67 references that are in the map. First posted on arXiv 17 Jan 2025.

Builds on

46 of 67 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2017Billion-scale similarity search with GPUscited by 2,477
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  10. 2013Describing Textures in the Wildcited by 2,110
  11. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
34 more
  1. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  4. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  5. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  6. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  7. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  8. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  9. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  10. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  11. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  12. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  13. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  14. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  15. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  16. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 203
  17. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  18. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  19. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  20. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  21. 2020Exactly Computing the Local Lipschitz Constant of ReLU Networkscited by 102
  22. 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
  23. 2019Metric Learning for Adversarial Robustnesscited by 77
  24. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  25. 2021Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environmentscited by 65
  26. 2023Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Needcited by 46
  27. 2022Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagationcited by 45
  28. 2022ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotationscited by 44
  29. 2018Deep Defense: Training DNNs with Improved Adversarial Robustnesscited by 41
  30. 2022Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspectivecited by 28
  31. 2020DSRNA: Differentiable Search of Robust Neural Architecturescited by 27
  32. 2022Adversarial vulnerability of powerful near out-of-distribution detectioncited by 16
  33. 2022READ: Aggregating Reconstruction Error into Out-of-distribution Detectioncited by 6
  34. 2022p-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representationscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Training ML Models with Predictable Failurescited by 0