# Are classical deep neural networks weakly adversarially robust?

arXiv: https://arxiv.org/abs/2506.02016 · HTML: https://mlsanity.com/paper/2506.02016/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 15 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 14 of 14)

- [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)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [A Law of Data Separation in Deep Learning](https://mlsanity.com/paper/2210.17020/) (2022)
- [Progressive Feedforward Collapse of ResNet Training](https://mlsanity.com/paper/2405.00985/) (2024)
- [Adversarial Sample Detection Through Neural Network Transport Dynamics](https://mlsanity.com/paper/2306.04252/) (2023)

## Abstract (arXiv)

Adversarial attacks have received increasing attention and it has been widely recognized that classical DNNs have weak adversarial robustness. The most commonly used adversarial defense method, adversarial training, improves the adversarial accuracy of DNNs by generating adversarial examples and retraining the model. However, adversarial training requires a significant computational overhead. In this paper, inspired by existing studies focusing on the clustering properties of DNN output features at each layer and the Progressive Feedforward Collapse phenomenon, we propose a method for adversarial example detection and image recognition that uses layer-wise features to construct feature paths and computes the correlation between the examples feature paths and the class-centered feature paths. Experimental results show that the recognition method achieves 82.77% clean accuracy and 44.17% adversarial accuracy on the ResNet-20 with PFC. Compared to the adversarial training method with 77.64% clean accuracy and 52.94% adversarial accuracy, our method exhibits a trade-off without relying on computationally expensive defense strategies. Furthermore, on the standard ResNet-18, our method maintains this advantage with respective metrics of 80.01% and 46.1%. This result reveals inherent adversarial robustness in DNNs, challenging the conventional understanding of the weak adversarial robustness in DNNs.