# Disrupting Deep Uncertainty Estimation Without Harming Accuracy

arXiv: https://arxiv.org/abs/2110.13741 · HTML: https://mlsanity.com/paper/2110.13741/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 47 references that are in the map.
- First posted on arXiv 26 Oct 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers](https://mlsanity.com/paper/1805.08206/) (2018)
- [Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?](https://mlsanity.com/paper/2010.14986/) (2020)

## Built on by (most cited first, 19 of 19)

- [Overcoming Common Flaws in the Evaluation of Selective Classification Systems](https://mlsanity.com/paper/2407.01032/) (2024)
- [Calibrating Multimodal Learning](https://mlsanity.com/paper/2306.01265/) (2023)
- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence](https://mlsanity.com/paper/2401.02718/) (2024)
- [Towards Certification of Uncertainty Calibration under Adversarial Attacks](https://mlsanity.com/paper/2405.13922/) (2024)
- [On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks](https://mlsanity.com/paper/2210.02191/) (2022)
- [On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks](https://mlsanity.com/paper/2507.06489/) (2025)
- [Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks](https://mlsanity.com/paper/2404.19640/) (2024)
- [On the Robustness of Adversarial Training Against Uncertainty Attacks](https://mlsanity.com/paper/2410.21952/) (2024)
- [Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting](https://mlsanity.com/paper/2402.14184/) (2024)
- [Integrating uncertainty quantification into randomized smoothing based robustness guarantees](https://mlsanity.com/paper/2410.20432/) (2024)
- [A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection](https://mlsanity.com/paper/2505.12586/) (2025)
- [Evasion Attacks Against Bayesian Predictive Models](https://mlsanity.com/paper/2506.09640/) (2025)
- [How Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustness](https://mlsanity.com/paper/2601.14519/) (2026)
- [Temperature Scaling Attack Disrupting Model Confidence in Federated Learning](https://mlsanity.com/paper/2602.06638/) (2026)
- [ECUASn: A family of metrics for principled evaluation of uncertainty-augmented systems](https://mlsanity.com/paper/2605.20490/) (2026)
- [The Confidence Trap: Calibration Attacks for Graph Neural Networks](https://mlsanity.com/paper/2606.08467/) (2026)
- [LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks](https://mlsanity.com/paper/2607.07745/) (2026)
- [Vision-Language Model Confidence Is Not a Property of the Answer](https://mlsanity.com/paper/2608.06571/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) have proven to be powerful predictors and are widely used for various tasks. Credible uncertainty estimation of their predictions, however, is crucial for their deployment in many risk-sensitive applications. In this paper we present a novel and simple attack, which unlike adversarial attacks, does not cause incorrect predictions but instead cripples the network's capacity for uncertainty estimation. The result is that after the attack, the DNN is more confident of its incorrect predictions than about its correct ones without having its accuracy reduced. We present two versions of the attack. The first scenario focuses on a black-box regime (where the attacker has no knowledge of the target network) and the second scenario attacks a white-box setting. The proposed attack is only required to be of minuscule magnitude for its perturbations to cause severe uncertainty estimation damage, with larger magnitudes resulting in completely unusable uncertainty estimations. We demonstrate successful attacks on three of the most popular uncertainty estimation methods: the vanilla softmax score, Deep Ensembles and MC-Dropout. Additionally, we show an attack on SelectiveNet, the selective classification architecture. We test the proposed attack on several contemporary architectures such as MobileNetV2 and EfficientNetB0, all trained to classify ImageNet.