# Edge Detectors Can Make Deep Convolutional Neural Networks More Robust

arXiv: https://arxiv.org/abs/2402.16479 · HTML: https://mlsanity.com/paper/2402.16479/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 26 Feb 2024.

## Builds on (most cited first, 27 of 27)

- [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)
- [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)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [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 Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [Recent Advances in Adversarial Training for Adversarial Robustness](https://mlsanity.com/paper/2102.01356/) (2021)
- [Adversarial Logit Pairing](https://mlsanity.com/paper/1803.06373/) (2018)
- [Adversarial Examples: Opportunities and Challenges](https://mlsanity.com/paper/1809.04790/) (2018)
- [Subspace Adversarial Training](https://mlsanity.com/paper/2111.12229/) (2021)
- [Why ResNet Works? Residuals Generalize](https://mlsanity.com/paper/1904.01367/) (2019)
- [Gradient Obfuscation Gives a False Sense of Security in Federated Learning](https://mlsanity.com/paper/2206.04055/) (2022)
- [Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients](https://mlsanity.com/paper/2009.13145/) (2020)
- [Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks](https://mlsanity.com/paper/2212.01806/) (2022)
- [Injecting Logical Constraints into Neural Networks via Straight-Through Estimators](https://mlsanity.com/paper/2307.04347/) (2023)
- [Part-Based Models Improve Adversarial Robustness](https://mlsanity.com/paper/2209.09117/) (2022)
- [A2: Efficient Automated Attacker for Boosting Adversarial Training](https://mlsanity.com/paper/2210.03543/) (2022)
- [Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?](https://mlsanity.com/paper/2212.01076/) (2022)
- [Recent Advances in Large Margin Learning](https://mlsanity.com/paper/2103.13598/) (2021)
- [Revisiting Outer Optimization in Adversarial Training](https://mlsanity.com/paper/2209.01199/) (2022)
- [Adversarial Margin Maximization Networks](https://mlsanity.com/paper/1911.05916/) (2019)

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

- [Generative Edge Detection with Stable Diffusion](https://mlsanity.com/paper/2410.03080/) (2024)
- [Image selective encryption analysis using mutual information in CNN based embedding space](https://mlsanity.com/paper/2508.08832/) (2025)

## Abstract (arXiv)

Deep convolutional neural networks (DCNN for short) are vulnerable to examples with small perturbations. Improving DCNN's robustness is of great significance to the safety-critical applications, such as autonomous driving and industry automation. Inspired by the principal way that human eyes recognize objects, i.e., largely relying on the shape features, this paper first employs the edge detectors as layer kernels and designs a binary edge feature branch (BEFB for short) to learn the binary edge features, which can be easily integrated into any popular backbone. The four edge detectors can learn the horizontal, vertical, positive diagonal, and negative diagonal edge features, respectively, and the branch is stacked by multiple Sobel layers (using edge detectors as kernels) and one threshold layer. The binary edge features learned by the branch, concatenated with the texture features learned by the backbone, are fed into the fully connected layers for classification. We integrate the proposed branch into VGG16 and ResNet34, respectively, and conduct experiments on multiple datasets. Experimental results demonstrate the BEFB is lightweight and has no side effects on training. And the accuracy of the BEFB integrated models is better than the original ones on all datasets when facing FGSM, PGD, and C&W attacks. Besides, BEFB integrated models equipped with the robustness enhancing techniques can achieve better classification accuracy compared to the original models. The work in this paper for the first time shows it is feasible to enhance the robustness of DCNNs through combining both shape-like features and texture features.