# Adversarial Robustness in Deep Learning: Attacks on Fragile Neurons

arXiv: https://arxiv.org/abs/2201.12347 · HTML: https://mlsanity.com/paper/2201.12347/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 31 Jan 2022.

## Builds on (most cited first, 13 of 13)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [On the (Statistical) Detection of Adversarial Examples](https://mlsanity.com/paper/1702.06280/) (2017)
- [Interpreting Deep Visual Representations via Network Dissection](https://mlsanity.com/paper/1711.05611/) (2017)
- [Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey](https://mlsanity.com/paper/2007.00753/) (2020)
- [MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples](https://mlsanity.com/paper/1711.08478/) (2017)
- [Spectral Metric for Dataset Complexity Assessment](https://mlsanity.com/paper/1905.07299/) (2019)
- [On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations](https://mlsanity.com/paper/1703.08245/) (2017)

## Built on by (most cited first, 3 of 3)

- [Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks](https://mlsanity.com/paper/2408.13102/) (2024)
- [Fragility, Robustness and Antifragility in Deep Learning](https://mlsanity.com/paper/2312.09821/) (2023)
- [SYNAPSE: Framework for Neuron Analysis and Perturbation in Sequence Encoding](https://mlsanity.com/paper/2603.08424/) (2026)

## Abstract (arXiv)

We identify fragile and robust neurons of deep learning architectures using nodal dropouts of the first convolutional layer. Using an adversarial targeting algorithm, we correlate these neurons with the distribution of adversarial attacks on the network. Adversarial robustness of neural networks has gained significant attention in recent times and highlights intrinsic weaknesses of deep learning networks against carefully constructed distortion applied to input images. In this paper, we evaluate the robustness of state-of-the-art image classification models trained on the MNIST and CIFAR10 datasets against the fast gradient sign method attack, a simple yet effective method of deceiving neural networks. Our method identifies the specific neurons of a network that are most affected by the adversarial attack being applied. We, therefore, propose to make fragile neurons more robust against these attacks by compressing features within robust neurons and amplifying the fragile neurons proportionally.