# Multi-head Uncertainty Inference for Adversarial Attack Detection

arXiv: https://arxiv.org/abs/2212.10006 · HTML: https://mlsanity.com/paper/2212.10006/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 20 Dec 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [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)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Certified Robustness to Adversarial Examples with Differential Privacy](https://mlsanity.com/paper/1802.03471/) (2018)
- [Recent Advances in Convolutional Neural Networks](https://mlsanity.com/paper/1512.07108/) (2015)
- [Certified Defenses against Adversarial Examples](https://mlsanity.com/paper/1801.09344/) (2018)
- [Recent Advances in Adversarial Training for Adversarial Robustness](https://mlsanity.com/paper/2102.01356/) (2021)
- [Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness](https://mlsanity.com/paper/1905.13472/) (2019)
- [Improving DNN Robustness to Adversarial Attacks using Jacobian Regularization](https://mlsanity.com/paper/1803.08680/) (2018)
- [Adversarial Examples that Fool both Computer Vision and Time-Limited Humans](https://mlsanity.com/paper/1802.08195/) (2018)
- [DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference](https://mlsanity.com/paper/2011.08595/) (2020)
- [Making a Bird AI Expert Work for You and Me](https://mlsanity.com/paper/2112.02747/) (2021)
- [BALSON: Bayesian Least Squares Optimization with Nonnegative L1-Norm Constraint](https://mlsanity.com/paper/1807.02795/) (2018)

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

- [Self-Supervised Representation Learning for Adversarial Attack Detection](https://mlsanity.com/paper/2407.04382/) (2024)
- [GradID: Adversarial Detection via Intrinsic Dimensionality of Gradients](https://mlsanity.com/paper/2512.12827/) (2025)

## Abstract (arXiv)

Deep neural networks (DNNs) are sensitive and susceptible to tiny perturbation by adversarial attacks which causes erroneous predictions. Various methods, including adversarial defense and uncertainty inference (UI), have been developed in recent years to overcome the adversarial attacks. In this paper, we propose a multi-head uncertainty inference (MH-UI) framework for detecting adversarial attack examples. We adopt a multi-head architecture with multiple prediction heads (i.e., classifiers) to obtain predictions from different depths in the DNNs and introduce shallow information for the UI. Using independent heads at different depths, the normalized predictions are assumed to follow the same Dirichlet distribution, and we estimate distribution parameter of it by moment matching. Cognitive uncertainty brought by the adversarial attacks will be reflected and amplified on the distribution. Experimental results show that the proposed MH-UI framework can outperform all the referred UI methods in the adversarial attack detection task with different settings.