# Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration

arXiv: https://arxiv.org/abs/2012.10923 · HTML: https://mlsanity.com/paper/2012.10923/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2020.

## Built on by (most cited first, 30 of 34)

- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [When and How Mixup Improves Calibration](https://mlsanity.com/paper/2102.06289/) (2021)
- [What Makes Graph Neural Networks Miscalibrated?](https://mlsanity.com/paper/2210.06391/) (2022)
- [Learn to Accumulate Evidence from All Training Samples: Theory and Practice](https://mlsanity.com/paper/2306.11113/) (2023)
- [Robust Models are less Over-Confident](https://mlsanity.com/paper/2210.05938/) (2022)
- [Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition](https://mlsanity.com/paper/2210.12256/) (2022)
- [CER: Confidence Enhanced Reasoning in LLMs](https://mlsanity.com/paper/2502.14634/) (2025)
- [Beyond In-Domain Scenarios: Robust Density-Aware Calibration](https://mlsanity.com/paper/2302.05118/) (2023)
- [Beyond Probability Partitions: Calibrating Neural Networks with Semantic Aware Grouping](https://mlsanity.com/paper/2306.04985/) (2023)
- [SimCalib: Graph Neural Network Calibration based on Similarity between Nodes](https://mlsanity.com/paper/2312.11858/) (2023)
- [On Calibration of Graph Neural Networks for Node Classification](https://mlsanity.com/paper/2206.01570/) (2022)
- [Training on Test Data with Bayesian Adaptation for Covariate Shift](https://mlsanity.com/paper/2109.12746/) (2021)
- [Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence](https://mlsanity.com/paper/2401.02718/) (2024)
- [Improved post-hoc probability calibration for out-of-domain MRI segmentation](https://mlsanity.com/paper/2208.02870/) (2022)
- [Understanding Calibration of Deep Neural Networks for Medical Image Classification](https://mlsanity.com/paper/2309.13132/) (2023)
- [Towards Certification of Uncertainty Calibration under Adversarial Attacks](https://mlsanity.com/paper/2405.13922/) (2024)
- [Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond](https://mlsanity.com/paper/2405.18925/) (2024)
- [Multi-Perspective Consistency Enhances Confidence Estimation in Large Language Models](https://mlsanity.com/paper/2402.11279/) (2024)
- [Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance](https://mlsanity.com/paper/2408.13648/) (2024)
- [Hyp-UML: Hyperbolic Image Retrieval with Uncertainty-aware Metric Learning](https://mlsanity.com/paper/2310.08390/) (2023)
- [How to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online Continual Learning](https://mlsanity.com/paper/2407.07668/) (2024)
- [Consistency-Guided Temperature Scaling Using Style and Content Information for Out-of-Domain Calibration](https://mlsanity.com/paper/2402.15019/) (2024)
- [Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation](https://mlsanity.com/paper/2512.23753/) (2025)
- [Hidden Heterogeneity: When to Choose Similarity-Based Calibration](https://mlsanity.com/paper/2202.01840/) (2022)
- [Rethinking and Recomputing the Value of Machine Learning Models](https://mlsanity.com/paper/2209.15157/) (2022)
- [Propagating Variational Model Uncertainty for Bioacoustic Call Label Smoothing](https://mlsanity.com/paper/2210.10526/) (2022)
- [Annealing Double-Head: An Architecture for Online Calibration of Deep Neural Networks](https://mlsanity.com/paper/2212.13621/) (2022)
- [U-Trustworthy Models.Reliability, Competence, and Confidence in Decision-Making](https://mlsanity.com/paper/2401.02062/) (2024)
- [Evidential learning driven Breast Tumor Segmentation with Stage-divided Vision-Language Interaction](https://mlsanity.com/paper/2603.11206/) (2026)
- [CHALLENGER: Training with Attribution Maps](https://mlsanity.com/paper/2205.15094/) (2022)

## Abstract (arXiv)

To facilitate a wide-spread acceptance of AI systems guiding decision making in real-world applications, trustworthiness of deployed models is key. That is, it is crucial for predictive models to be uncertainty-aware and yield well-calibrated (and thus trustworthy) predictions for both in-domain samples as well as under domain shift. Recent efforts to account for predictive uncertainty include post-processing steps for trained neural networks, Bayesian neural networks as well as alternative non-Bayesian approaches such as ensemble approaches and evidential deep learning. Here, we propose an efficient yet general modelling approach for obtaining well-calibrated, trustworthy probabilities for samples obtained after a domain shift. We introduce a new training strategy combining an entropy-encouraging loss term with an adversarial calibration loss term and demonstrate that this results in well-calibrated and technically trustworthy predictions for a wide range of domain drifts. We comprehensively evaluate previously proposed approaches on different data modalities, a large range of data sets including sequence data, network architectures and perturbation strategies. We observe that our modelling approach substantially outperforms existing state-of-the-art approaches, yielding well-calibrated predictions under domain drift.