# Delving into the pixels of adversarial samples

arXiv: https://arxiv.org/abs/2106.10996 · HTML: https://mlsanity.com/paper/2106.10996/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 32 references that are in the map.
- First posted on arXiv 21 Jun 2021.

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

- [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)
- [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)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [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)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Adversarial Robustness Toolbox v1.0.0](https://mlsanity.com/paper/1807.01069/) (2018)
- [The Space of Transferable Adversarial Examples](https://mlsanity.com/paper/1704.03453/) (2017)
- [Enhancing Adversarial Example Transferability with an Intermediate Level Attack](https://mlsanity.com/paper/1907.10823/) (2019)
- [Adversarial Attacks and Defences Competition](https://mlsanity.com/paper/1804.00097/) (2018)
- [Backpropagating Linearly Improves Transferability of Adversarial Examples](https://mlsanity.com/paper/2012.03528/) (2020)
- [Defensive Distillation is Not Robust to Adversarial Examples](https://mlsanity.com/paper/1607.04311/) (2016)
- [Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability](https://mlsanity.com/paper/2004.14861/) (2020)
- [Adversarial Manipulation of Deep Representations](https://mlsanity.com/paper/1511.05122/) (2015)
- [Transferable Perturbations of Deep Feature Distributions](https://mlsanity.com/paper/2004.12519/) (2020)
- [MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples](https://mlsanity.com/paper/1711.08478/) (2017)

## Built on by (most cited first, 1 of 1)

- [ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP](https://mlsanity.com/paper/2511.17362/) (2025)

## Abstract (arXiv)

Despite extensive research into adversarial attacks, we do not know how adversarial attacks affect image pixels. Knowing how image pixels are affected by adversarial attacks has the potential to lead us to better adversarial defenses. Motivated by instances that we find where strong attacks do not transfer, we delve into adversarial examples at pixel level to scrutinize how adversarial attacks affect image pixel values. We consider several ImageNet architectures, InceptionV3, VGG19 and ResNet50, as well as several strong attacks. We find that attacks can have different effects at pixel level depending on classifier architecture. In particular, input pre-processing plays a previously overlooked role in the effect that attacks have on pixels. Based on the insights of pixel-level examination, we find new ways to detect some of the strongest current attacks.