mlsanityData to 7 Oct 2026

Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?

arXiv 2010.14986 ↗First posted 28 Oct 2020cs.LG stat.MLcited by 39

Not on the map. Why?

Abstract (arXiv)

Dirichlet-based uncertainty (DBU) models are a recent and promising class of uncertainty-aware models. DBU models predict the parameters of a Dirichlet distribution to provide fast, high-quality uncertainty estimates alongside with class predictions. In this work, we present the first large-scale, in-depth study of the robustness of DBU models under adversarial attacks. Our results suggest that uncertainty estimates of DBU models are not robust w.r.t. three important tasks: (1) indicating correctly and wrongly classified samples; (2) detecting adversarial examples; and (3) distinguishing between in-distribution (ID) and out-of-distribution (OOD) data. Additionally, we explore the first approaches to make DBU models more robust. While adversarial training has a minor effect, our median smoothing based approach significantly increases robustness of DBU models.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 6; 2023: 8; 2024: 6; 2025: 6; 2026: 7.

39 papers.

Sort:

By area:

  1. 2022Trusted Multi-View Classification with Dynamic Evidential Fusioncited by 167
  2. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 124
  3. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  4. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  5. 2022Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisationcited by 65
  6. 2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44
  7. 2023On Second-Order Scoring Rules for Epistemic Uncertainty Quantificationcited by 38
  8. 2024Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?cited by 34
  9. 2023Learn to Accumulate Evidence from All Training Samples: Theory and Practicecited by 28
  10. 2022Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learningcited by 27
  11. 2022Towards Open Set Video Anomaly Detectioncited by 26
  12. 2021Disrupting Deep Uncertainty Estimation Without Harming Accuracycited by 19
27 more
  1. 2023Random-Set Neural Networks (RS-NN)cited by 19
  2. 2021Provably Robust Detection of Out-of-distribution Data (almost) for freecited by 17
  3. 2021Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributionscited by 13
  4. 2023Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shiftscited by 12
  5. 2023Uncertainty Estimation for Molecules: Desiderata and Methodscited by 11
  6. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 11
  7. 2021Dense Uncertainty Estimationcited by 9
  8. 2022On the Calibration of Probabilistic Classifier Setscited by 8
  9. 2025Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'cited by 8
  10. 2025Position: Epistemic uncertainty estimation methods are fundamentally incompletecited by 8
  11. 2023E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognitioncited by 7
  12. 2025A calibration test for evaluating set-based epistemic uncertainty representationscited by 7
  13. 2024Towards Certification of Uncertainty Calibration under Adversarial Attackscited by 5
  14. 2023Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustnesscited by 2
  15. 2024Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networkscited by 2
  16. 2024Linear Opinion Pooling for Uncertainty Quantification on Graphscited by 2
  17. 2025Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learningcited by 2
  18. 2025Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluationcited by 2
  19. 2026Evidential learning driven Breast Tumor Segmentation with Stage-divided Vision-Language Interactioncited by 1
  20. 2024Modeling Weather Uncertainty for Multi-weather Co-Presence Estimationcited by 0
  21. 2024CUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networkscited by 0
  22. 2026A Robust Out-of-Distribution Detection Framework via Synergistic Smoothingcited by 0
  23. 2026The Confidence Trap: Calibration Attacks for Graph Neural Networkscited by 0
  24. 2026Reinforcement Learning Disrupts Gradient-Based Adversarial Optimizationcited by 0
  25. 2026ELDiff: When Evidential Learning Meets Text-to-Image Diffusioncited by 0
  26. 2026Vision-Language Model Confidence Is Not a Property of the Answercited by 0
  27. 2026Robust Evidential Learning Through Latent Consistencycited by 0