mlsanityData to 7 Oct 2026

Improving Calibration through the Relationship with Adversarial Robustness

arXiv 2006.16375 ↗First posted 29 Jun 2020cs.LG stat.MLcited by 26

Not on the map. Why?

Abstract (arXiv)

Neural networks lack adversarial robustness, i.e., they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trust is undermined when models give miscalibrated predictions, i.e., the predicted probability is not a good indicator of how much we should trust our model. In this paper, we study the connection between adversarial robustness and calibration and find that the inputs for which the model is sensitive to small perturbations (are easily attacked) are more likely to have poorly calibrated predictions. Based on this insight, we examine if calibration can be improved by addressing those adversarially unrobust inputs. To this end, we propose Adversarial Robustness based Adaptive Label Smoothing (AR-AdaLS) that integrates the correlations of adversarial robustness and calibration into training by adaptively softening labels for an example based on how easily it can be attacked by an adversary. We find that our method, taking the adversarial robustness of the in-distribution data into consideration, leads to better calibration over the model even under distributional shifts. In addition, AR-AdaLS can also be applied to an ensemble model to further improve model calibration.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 7; 2024: 5; 2025: 3; 2026: 3.

26 papers.

Sort:

  1. 2022Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysiscited by 104
  2. 2023Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Methodcited by 51
  3. 2021Are Vision Transformers Robust to Patch Perturbations?cited by 39
  4. 2022Robust Models are less Over-Confidentcited by 25
  5. 2022Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attackscited by 18
  6. 2023Calibrating Multimodal Learningcited by 17
  7. 2023Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learningcited by 11
  8. 2024The Pitfalls and Promise of Conformal Inference Under Adversarial Attackscited by 8
  9. 2022Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimatescited by 7
  10. 2023Annealing Self-Distillation Rectification Improves Adversarial Trainingcited by 7
  11. 2024Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidencecited by 7
  12. 2023What Are Effective Labels for Augmented Data? Improving Calibration and Robustness with AutoLabelcited by 6
14 more
  1. 2024Minimum Topology Attacks for Graph Neural Networkscited by 6
  2. 2022In and Out-of-Domain Text Adversarial Robustness via Label Smoothingcited by 5
  3. 2024Towards Certification of Uncertainty Calibration under Adversarial Attackscited by 5
  4. 2022Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibrationcited by 4
  5. 2022Improving Generalization via Uncertainty Driven Perturbationscited by 3
  6. 2023Robust Feature Inference: A Test-time Defense Strategy using Spectral Projectionscited by 3
  7. 2026Too Sharp, Too Sure: When Calibration Follows Curvaturecited by 2
  8. 2023Survival Analysis with Adversarial Regularizationcited by 0
  9. 2024Batch-in-Batch: a new adversarial training framework for initial perturbation and sample selectioncited by 0
  10. 2025Confidence Regularized Masked Language Modeling using Text Lengthcited by 0
  11. 2025Weak Links in LinkedIn: Enhancing Fake Profile Detection in the Age of LLMscited by 0
  12. 2025The Power of Many: Synergistic Unification of Diverse Augmentations for Efficient Adversarial Robustnesscited by 0
  13. 2026Reinforcement Learning Disrupts Gradient-Based Adversarial Optimizationcited by 0
  14. 2026LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networkscited by 0