Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201499076> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3201499076 endingPage "18" @default.
- W3201499076 startingPage "1" @default.
- W3201499076 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." @default.
- W3201499076 created "2021-09-27" @default.
- W3201499076 creator A5006013473 @default.
- W3201499076 creator A5071320926 @default.
- W3201499076 date "2021-09-13" @default.
- W3201499076 modified "2023-10-16" @default.
- W3201499076 title "Adversarial Sample Detection with Gaussian Mixture Conditional Generative Adversarial Networks" @default.
- W3201499076 cites W2194775991 @default.
- W3201499076 cites W2535873859 @default.
- W3201499076 cites W2963073614 @default.
- W3201499076 cites W2963446712 @default.
- W3201499076 cites W2964149421 @default.
- W3201499076 cites W2964159205 @default.
- W3201499076 cites W639708223 @default.
- W3201499076 doi "https://doi.org/10.1155/2021/8268249" @default.
- W3201499076 hasPublicationYear "2021" @default.
- W3201499076 type Work @default.
- W3201499076 sameAs 3201499076 @default.
- W3201499076 citedByCount "0" @default.
- W3201499076 crossrefType "journal-article" @default.
- W3201499076 hasAuthorship W3201499076A5006013473 @default.
- W3201499076 hasAuthorship W3201499076A5071320926 @default.
- W3201499076 hasBestOaLocation W32014990761 @default.
- W3201499076 hasConcept C108583219 @default.
- W3201499076 hasConcept C111919701 @default.
- W3201499076 hasConcept C118505674 @default.
- W3201499076 hasConcept C119857082 @default.
- W3201499076 hasConcept C121332964 @default.
- W3201499076 hasConcept C153180895 @default.
- W3201499076 hasConcept C154945302 @default.
- W3201499076 hasConcept C163716315 @default.
- W3201499076 hasConcept C2779803651 @default.
- W3201499076 hasConcept C2988773926 @default.
- W3201499076 hasConcept C37736160 @default.
- W3201499076 hasConcept C39890363 @default.
- W3201499076 hasConcept C41008148 @default.
- W3201499076 hasConcept C50644808 @default.
- W3201499076 hasConcept C62520636 @default.
- W3201499076 hasConcept C76155785 @default.
- W3201499076 hasConcept C94915269 @default.
- W3201499076 hasConcept C95623464 @default.
- W3201499076 hasConceptScore W3201499076C108583219 @default.
- W3201499076 hasConceptScore W3201499076C111919701 @default.
- W3201499076 hasConceptScore W3201499076C118505674 @default.
- W3201499076 hasConceptScore W3201499076C119857082 @default.
- W3201499076 hasConceptScore W3201499076C121332964 @default.
- W3201499076 hasConceptScore W3201499076C153180895 @default.
- W3201499076 hasConceptScore W3201499076C154945302 @default.
- W3201499076 hasConceptScore W3201499076C163716315 @default.
- W3201499076 hasConceptScore W3201499076C2779803651 @default.
- W3201499076 hasConceptScore W3201499076C2988773926 @default.
- W3201499076 hasConceptScore W3201499076C37736160 @default.
- W3201499076 hasConceptScore W3201499076C39890363 @default.
- W3201499076 hasConceptScore W3201499076C41008148 @default.
- W3201499076 hasConceptScore W3201499076C50644808 @default.
- W3201499076 hasConceptScore W3201499076C62520636 @default.
- W3201499076 hasConceptScore W3201499076C76155785 @default.
- W3201499076 hasConceptScore W3201499076C94915269 @default.
- W3201499076 hasConceptScore W3201499076C95623464 @default.
- W3201499076 hasFunder F4320336311 @default.
- W3201499076 hasLocation W32014990761 @default.
- W3201499076 hasLocation W32014990762 @default.
- W3201499076 hasOpenAccess W3201499076 @default.
- W3201499076 hasPrimaryLocation W32014990761 @default.
- W3201499076 hasRelatedWork W2412510955 @default.
- W3201499076 hasRelatedWork W2808862658 @default.
- W3201499076 hasRelatedWork W2884614645 @default.
- W3201499076 hasRelatedWork W2919933730 @default.
- W3201499076 hasRelatedWork W2952541330 @default.
- W3201499076 hasRelatedWork W2956709364 @default.
- W3201499076 hasRelatedWork W2973228473 @default.
- W3201499076 hasRelatedWork W3094555598 @default.
- W3201499076 hasRelatedWork W3202656664 @default.
- W3201499076 hasRelatedWork W4280544492 @default.
- W3201499076 hasVolume "2021" @default.
- W3201499076 isParatext "false" @default.
- W3201499076 isRetracted "false" @default.
- W3201499076 magId "3201499076" @default.
- W3201499076 workType "article" @default.