# Real-time Detection of Practical Universal Adversarial Perturbations

arXiv: https://arxiv.org/abs/2105.07334 · HTML: https://mlsanity.com/paper/2105.07334/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 45 references that are in the map.
- First posted on arXiv 16 May 2021.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (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)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [Fooling automated surveillance cameras: adversarial patches to attack person detection](https://mlsanity.com/paper/1904.08653/) (2019)
- [Adversarial Training and Robustness for Multiple Perturbations](https://mlsanity.com/paper/1904.13000/) (2019)
- [Physical Adversarial Examples for Object Detectors](https://mlsanity.com/paper/1807.07769/) (2018)
- [SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems](https://mlsanity.com/paper/1812.00292/) (2018)
- [DPatch: An Adversarial Patch Attack on Object Detectors](https://mlsanity.com/paper/1806.02299/) (2018)
- [Physically Realizable Adversarial Examples for LiDAR Object Detection](https://mlsanity.com/paper/2004.00543/) (2020)
- [Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations](https://mlsanity.com/paper/1801.08092/) (2018)
- [Universal Adversarial Training](https://mlsanity.com/paper/1811.11304/) (2018)
- [Fast Feature Fool: A data independent approach to universal adversarial perturbations](https://mlsanity.com/paper/1707.05572/) (2017)
- [Adversarial Objects Against LiDAR-Based Autonomous Driving Systems](https://mlsanity.com/paper/1907.05418/) (2019)
- [Art of singular vectors and universal adversarial perturbations](https://mlsanity.com/paper/1709.03582/) (2017)
- [Defense against Universal Adversarial Perturbations](https://mlsanity.com/paper/1711.05929/) (2017)
- [On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions](https://mlsanity.com/paper/1809.04098/) (2018)
- [Defending Against Universal Perturbations With Shared Adversarial Training](https://mlsanity.com/paper/1812.03705/) (2018)
- [Transfer of Adversarial Robustness Between Perturbation Types](https://mlsanity.com/paper/1905.01034/) (2019)

## Built on by (most cited first, 6 of 6)

- [On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving](https://mlsanity.com/paper/2201.01850/) (2022)
- [Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey](https://mlsanity.com/paper/2206.08304/) (2022)
- [Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis](https://mlsanity.com/paper/2203.07341/) (2022)
- [CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Models](https://mlsanity.com/paper/2206.04365/) (2022)
- [Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications](https://mlsanity.com/paper/2311.11191/) (2023)
- [SpaNN: Detecting Multiple Adversarial Patches on CNNs by Spanning Saliency Thresholds](https://mlsanity.com/paper/2506.18591/) (2025)

## Abstract (arXiv)

Universal Adversarial Perturbations (UAPs) are a prominent class of adversarial examples that exploit the systemic vulnerabilities and enable physically realizable and robust attacks against Deep Neural Networks (DNNs). UAPs generalize across many different inputs; this leads to realistic and effective attacks that can be applied at scale. In this paper we propose HyperNeuron, an efficient and scalable algorithm that allows for the real-time detection of UAPs by identifying suspicious neuron hyper-activations. Our results show the effectiveness of HyperNeuron on multiple tasks (image classification, object detection), against a wide variety of universal attacks, and in realistic scenarios, like perceptual ad-blocking and adversarial patches. HyperNeuron is able to simultaneously detect both adversarial mask and patch UAPs with comparable or better performance than existing UAP defenses whilst introducing a significantly reduced latency of only 0.86 milliseconds per image. This suggests that many realistic and practical universal attacks can be reliably mitigated in real-time, which shows promise for the robust deployment of machine learning systems.