当前位置: X-MOL 学术Math. Probl. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Adversarial Sample Detection with Gaussian Mixture Conditional Generative Adversarial Networks
Mathematical Problems in Engineering Pub Date : 2021-09-13 , DOI: 10.1155/2021/8268249
Pengfei Zhang 1 , Xiaoming Ju 1
Affiliation  

It is important to detect adversarial samples in the physical world that are far away from the training data distribution. Some adversarial samples can make a machine learning model generate a highly overconfident distribution in the testing stage. Thus, we proposed a mechanism for detecting adversarial samples based on semisupervised generative adversarial networks (GANs) with an encoder-decoder structure; this mechanism can be applied to any pretrained neural network without changing the network’s structure. The semisupervised GANs also give us insight into the behavior of adversarial samples and their flow through the layers of a deep neural network. In the supervised scenario, the latent feature of the semisupervised GAN and the target network’s logit information are used as the input of the external classifier support vector machine to detect the adversarial samples. In the unsupervised scenario, first, we proposed a one-class classier based on the semisupervised Gaussian mixture conditional generative adversarial network (GM-CGAN) to fit the joint feature information of the normal data, and then, we used a discriminator network to detect normal data and adversarial samples. In both supervised scenarios and unsupervised scenarios, experimental results show that our method outperforms latest methods.

中文翻译:

使用高斯混合条件生成对抗网络进行对抗样本检测

检测物理世界中远离训练数据分布的对抗样本很重要。一些对抗样本可以使机器学习模型在测试阶段生成高度过度自信的分布。因此,我们提出了一种基于具有编码器-解码器结构的半监督生成对抗网络(GAN)检测对抗样本的机制;这种机制可以应用于任何预训练的神经网络,而无需改变网络结构。半监督 GAN 还让我们深入了解对抗样本的行为及其在深度神经网络层中的流动。在监督场景中,将半监督 GAN 的潜在特征和目标网络的 logit 信息作为外部分类器支持向量机的输入来检测对抗样本。在无监督场景中,我们首先提出了一个基于半监督高斯混合条件生成对抗网络(GM-CGAN)的一类分类器来拟合正常数据的联合特征信息,然后,我们使用一个鉴别器网络来检测正常数据和对抗样本。在监督场景和无监督场景中,实验结果表明我们的方法优于最新方法。我们提出了一种基于半监督高斯混合条件生成对抗网络(GM-CGAN)的一类分类器来拟合正常数据的联合特征信息,然后我们使用鉴别器网络来检测正常数据和对抗样本。在监督场景和无监督场景中,实验结果表明我们的方法优于最新方法。我们提出了一种基于半监督高斯混合条件生成对抗网络(GM-CGAN)的一类分类器来拟合正常数据的联合特征信息,然后我们使用鉴别器网络来检测正常数据和对抗样本。在监督场景和无监督场景中,实验结果表明我们的方法优于最新方法。
更新日期:2021-09-13
down
wechat
bug