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.
翻译:随着技术的迅速发展,进化神经网络的应用改善了我们生活的方便性,然而,在图像分类领域,人们发现,如果将一些干扰添加到图像中,CNN会错误地分类。因此提出了各种防御方法。以前的方法只是考虑如何将模块纳入网络以提高稳健性,而没有侧重于模块的整合方式。在本文中,我们设计了新的聚合方法,以加强CNN的稳健性。我们使用基于点的产品法,在ResNet18中添加去除模块和关注机制,以进一步提高模型的稳健性。CIFAR10的实验结果表明,我们的方法比FGSM和PGD攻击下的最新方法更有效和更好。