# An Effective Fusion Method to Enhance the Robustness of CNN

arXiv: https://arxiv.org/abs/2205.15582 · HTML: https://mlsanity.com/paper/2205.15582/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 31 May 2022.

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

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser](https://mlsanity.com/paper/1712.02976/) (2017)
- [HashNet: Deep Learning to Hash by Continuation](https://mlsanity.com/paper/1702.00758/) (2017)
- [On Robustness of Neural Ordinary Differential Equations](https://mlsanity.com/paper/1910.05513/) (2019)
- [Improving Adversarial Robustness via Channel-wise Activation Suppressing](https://mlsanity.com/paper/2103.08307/) (2021)
- [Sparse DNNs with Improved Adversarial Robustness](https://mlsanity.com/paper/1810.09619/) (2018)
- [Deep Defense: Training DNNs with Improved Adversarial Robustness](https://mlsanity.com/paper/1803.00404/) (2018)
- [Supervised Discrete Hashing](https://mlsanity.com/paper/1503.01557/) (2015)
- [Deep Supervised Hashing with Triplet Labels](https://mlsanity.com/paper/1612.03900/) (2016)
- [Deep Ordinal Hashing with Spatial Attention](https://mlsanity.com/paper/1805.02459/) (2018)

## Abstract (arXiv)

With the development of technology rapidly, applications of convolutional neural networks have improved the convenience of our life. However, in image classification field, it has been found that when some perturbations are added to images, the CNN would misclassify it. Thus various defense methods have been proposed. The previous approach only considered how to incorporate modules in the network to improve robustness, but did not focus on the way the modules were incorporated. In this paper, we design a new fusion method to enhance the robustness of CNN. We use a dot product-based approach to add the denoising module to ResNet18 and the attention mechanism to further improve the robustness of the model. The experimental results on CIFAR10 have shown that our method is effective and better than the state-of-the-art methods under the attack of FGSM and PGD.