# Improving Calibration through the Relationship with Adversarial Robustness

arXiv: https://arxiv.org/abs/2006.16375 · HTML: https://mlsanity.com/paper/2006.16375/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2020.

## Built on by (most cited first, 26 of 26)

- [Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis](https://mlsanity.com/paper/2210.04714/) (2022)
- [Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method](https://mlsanity.com/paper/2310.17918/) (2023)
- [Are Vision Transformers Robust to Patch Perturbations?](https://mlsanity.com/paper/2111.10659/) (2021)
- [Robust Models are less Over-Confident](https://mlsanity.com/paper/2210.05938/) (2022)
- [Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks](https://mlsanity.com/paper/2205.12134/) (2022)
- [Calibrating Multimodal Learning](https://mlsanity.com/paper/2306.01265/) (2023)
- [Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning](https://mlsanity.com/paper/2307.07250/) (2023)
- [The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks](https://mlsanity.com/paper/2405.08886/) (2024)
- [Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates](https://mlsanity.com/paper/2211.03041/) (2022)
- [Annealing Self-Distillation Rectification Improves Adversarial Training](https://mlsanity.com/paper/2305.12118/) (2023)
- [Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence](https://mlsanity.com/paper/2401.02718/) (2024)
- [What Are Effective Labels for Augmented Data? Improving Calibration and Robustness with AutoLabel](https://mlsanity.com/paper/2302.11188/) (2023)
- [Minimum Topology Attacks for Graph Neural Networks](https://mlsanity.com/paper/2403.02723/) (2024)
- [In and Out-of-Domain Text Adversarial Robustness via Label Smoothing](https://mlsanity.com/paper/2212.10258/) (2022)
- [Towards Certification of Uncertainty Calibration under Adversarial Attacks](https://mlsanity.com/paper/2405.13922/) (2024)
- [Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration](https://mlsanity.com/paper/2209.11604/) (2022)
- [Improving Generalization via Uncertainty Driven Perturbations](https://mlsanity.com/paper/2202.05737/) (2022)
- [Robust Feature Inference: A Test-time Defense Strategy using Spectral Projections](https://mlsanity.com/paper/2307.11672/) (2023)
- [Too Sharp, Too Sure: When Calibration Follows Curvature](https://mlsanity.com/paper/2604.20614/) (2026)
- [Survival Analysis with Adversarial Regularization](https://mlsanity.com/paper/2312.16019/) (2023)
- [Batch-in-Batch: a new adversarial training framework for initial perturbation and sample selection](https://mlsanity.com/paper/2406.04070/) (2024)
- [Confidence Regularized Masked Language Modeling using Text Length](https://mlsanity.com/paper/2504.06037/) (2025)
- [Weak Links in LinkedIn: Enhancing Fake Profile Detection in the Age of LLMs](https://mlsanity.com/paper/2507.16860/) (2025)
- [The Power of Many: Synergistic Unification of Diverse Augmentations for Efficient Adversarial Robustness](https://mlsanity.com/paper/2508.03213/) (2025)
- [Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization](https://mlsanity.com/paper/2606.12251/) (2026)
- [LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks](https://mlsanity.com/paper/2607.07745/) (2026)

## 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.