Adversarial Sample Detection with Gaussian Mixture Conditional Generative Adversarial Networks

Pengfei Zhang, Xiaoming Ju and Jie Chen

Mathematical Problems in Engineering, 2021, vol. 2021, 1-18

Abstract: 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 (or the discriminator’s output score information) of the semi-supervised GAN and the target network's logit information are used as the input of logistic regression classifier 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.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
http://downloads.hindawi.com/journals/mpe/8268249.pdf (application/pdf)
http://downloads.hindawi.com/journals/mpe/8268249.xml (application/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:jnlmpe:8268249

DOI: 10.1155/2021/8268249

Access Statistics for this article

More articles in Mathematical Problems in Engineering from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().