# Detection of Uncertainty in Exceedance of Threshold (DUET): An Adversarial Patch Localizer

arXiv: https://arxiv.org/abs/2303.10291 · HTML: https://mlsanity.com/paper/2303.10291/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 18 Mar 2023.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Provable defenses against adversarial examples via the convex outer adversarial polytope](https://mlsanity.com/paper/1711.00851/) (2017)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [Accurate Uncertainties for Deep Learning Using Calibrated Regression](https://mlsanity.com/paper/1807.00263/) (2018)
- [Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality](https://mlsanity.com/paper/1801.02613/) (2018)
- [Detecting Adversarial Samples from Artifacts](https://mlsanity.com/paper/1703.00410/) (2017)
- [Bayesian Neural Network Priors Revisited](https://mlsanity.com/paper/2102.06571/) (2021)
- [On Physical Adversarial Patches for Object Detection](https://mlsanity.com/paper/1906.11897/) (2019)
- [Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network](https://mlsanity.com/paper/1810.01279/) (2018)
- [ML-LOO: Detecting Adversarial Examples with Feature Attribution](https://mlsanity.com/paper/1906.03499/) (2019)
- [LiBRe: A Practical Bayesian Approach to Adversarial Detection](https://mlsanity.com/paper/2103.14835/) (2021)
- [Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation](https://mlsanity.com/paper/2108.01634/) (2021)
- [LanCe: A Comprehensive and Lightweight CNN Defense Methodology against Physical Adversarial Attacks on Embedded Multimedia Applications](https://mlsanity.com/paper/1910.08536/) (2019)
- [On the Limitation of Local Intrinsic Dimensionality for Characterizing the Subspaces of Adversarial Examples](https://mlsanity.com/paper/1803.09638/) (2018)
- [Detecting Patch Adversarial Attacks with Image Residuals](https://mlsanity.com/paper/2002.12504/) (2020)
- [Adversarial Examples Detection with Bayesian Neural Network](https://mlsanity.com/paper/2105.08620/) (2021)
- [In Depth Bayesian Semantic Scene Completion](https://mlsanity.com/paper/2010.08310/) (2020)

## Built on by (most cited first, 2 of 2)

- [Don't Lag, RAG: Training-Free Adversarial Detection Using RAG](https://mlsanity.com/paper/2504.04858/) (2025)
- [Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attacks](https://mlsanity.com/paper/2403.12988/) (2024)

## Abstract (arXiv)

Development of defenses against physical world attacks such as adversarial patches is gaining traction within the research community. We contribute to the field of adversarial patch detection by introducing an uncertainty-based adversarial patch localizer which localizes adversarial patch on an image, permitting post-processing patch-avoidance or patch-reconstruction. We quantify our prediction uncertainties with the development of textitDetection of Uncertainties in the Exceedance of Threshold (DUET) algorithm. This algorithm provides a framework to ascertain confidence in the adversarial patch localization, which is essential for safety-sensitive applications such as self-driving cars and medical imaging. We conducted experiments on localizing adversarial patches and found our proposed DUET model outperforms baseline models. We then conduct further analyses on our choice of model priors and the adoption of Bayesian Neural Networks in different layers within our model architecture. We found that isometric gaussian priors in Bayesian Neural Networks are suitable for patch localization tasks and the presence of Bayesian layers in the earlier neural network blocks facilitates top-end localization performance, while Bayesian layers added in the later neural network blocks contribute to better model generalization. We then propose two different well-performing models to tackle different use cases.