# Deep neural network loses attention to adversarial images

arXiv: https://arxiv.org/abs/2106.05657 · HTML: https://mlsanity.com/paper/2106.05657/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 10 Jun 2021.

## Builds on (most cited first, 18 of 18)

- [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)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [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)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [Adversarial Robustness Toolbox v1.0.0](https://mlsanity.com/paper/1807.01069/) (2018)
- [Understanding the One-Pixel Attack: Propagation Maps and Locality Analysis](https://mlsanity.com/paper/1902.02947/) (2019)

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

- [A reading survey on adversarial machine learning: Adversarial attacks and their understanding](https://mlsanity.com/paper/2308.03363/) (2023)
- [Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning](https://mlsanity.com/paper/2311.07928/) (2023)

## Abstract (arXiv)

Adversarial algorithms have shown to be effective against neural networks for a variety of tasks. Some adversarial algorithms perturb all the pixels in the image minimally for the image classification task in image classification. In contrast, some algorithms perturb few pixels strongly. However, very little information is available regarding why these adversarial samples so diverse from each other exist. Recently, Vargas et al. showed that the existence of these adversarial samples might be due to conflicting saliency within the neural network. We test this hypothesis of conflicting saliency by analysing the Saliency Maps (SM) and Gradient-weighted Class Activation Maps (Grad-CAM) of original and few different types of adversarial samples. We also analyse how different adversarial samples distort the attention of the neural network compared to original samples. We show that in the case of Pixel Attack, perturbed pixels either calls the network attention to themselves or divert the attention from them. Simultaneously, the Projected Gradient Descent Attack perturbs pixels so that intermediate layers inside the neural network lose attention for the correct class. We also show that both attacks affect the saliency map and activation maps differently. Thus, shedding light on why some defences successful against some attacks remain vulnerable against other attacks. We hope that this analysis will improve understanding of the existence and the effect of adversarial samples and enable the community to develop more robust neural networks.