Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385327857> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4385327857 abstract "Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source model can fool another black-box model (target model) with a non-trivial probability. In previous studies, it was confirmed that the vision transformer (ViT) is more robust against the property of adversarial transferability than convolutional neural network (CNN) models such as ConvMixer, and moreover encrypted ViT is more robust than ViT without any encryption. In this article, we propose a random ensemble of encrypted ViT models to achieve much more robust models. In experiments, the proposed scheme is verified to be more robust against not only black-box attacks but also white-box ones than convention methods." @default.
- W4385327857 created "2023-07-28" @default.
- W4385327857 creator A5005323356 @default.
- W4385327857 creator A5015250468 @default.
- W4385327857 creator A5054076544 @default.
- W4385327857 creator A5067910092 @default.
- W4385327857 date "2023-07-26" @default.
- W4385327857 modified "2023-09-27" @default.
- W4385327857 title "Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Models" @default.
- W4385327857 doi "https://doi.org/10.48550/arxiv.2307.13985" @default.
- W4385327857 hasPublicationYear "2023" @default.
- W4385327857 type Work @default.
- W4385327857 citedByCount "0" @default.
- W4385327857 crossrefType "posted-content" @default.
- W4385327857 hasAuthorship W4385327857A5005323356 @default.
- W4385327857 hasAuthorship W4385327857A5015250468 @default.
- W4385327857 hasAuthorship W4385327857A5054076544 @default.
- W4385327857 hasAuthorship W4385327857A5067910092 @default.
- W4385327857 hasBestOaLocation W43853278571 @default.
- W4385327857 hasConcept C108583219 @default.
- W4385327857 hasConcept C119857082 @default.
- W4385327857 hasConcept C140331021 @default.
- W4385327857 hasConcept C148730421 @default.
- W4385327857 hasConcept C153180895 @default.
- W4385327857 hasConcept C154945302 @default.
- W4385327857 hasConcept C180932941 @default.
- W4385327857 hasConcept C37736160 @default.
- W4385327857 hasConcept C38652104 @default.
- W4385327857 hasConcept C41008148 @default.
- W4385327857 hasConcept C61272859 @default.
- W4385327857 hasConcept C81363708 @default.
- W4385327857 hasConceptScore W4385327857C108583219 @default.
- W4385327857 hasConceptScore W4385327857C119857082 @default.
- W4385327857 hasConceptScore W4385327857C140331021 @default.
- W4385327857 hasConceptScore W4385327857C148730421 @default.
- W4385327857 hasConceptScore W4385327857C153180895 @default.
- W4385327857 hasConceptScore W4385327857C154945302 @default.
- W4385327857 hasConceptScore W4385327857C180932941 @default.
- W4385327857 hasConceptScore W4385327857C37736160 @default.
- W4385327857 hasConceptScore W4385327857C38652104 @default.
- W4385327857 hasConceptScore W4385327857C41008148 @default.
- W4385327857 hasConceptScore W4385327857C61272859 @default.
- W4385327857 hasConceptScore W4385327857C81363708 @default.
- W4385327857 hasLocation W43853278571 @default.
- W4385327857 hasOpenAccess W4385327857 @default.
- W4385327857 hasPrimaryLocation W43853278571 @default.
- W4385327857 hasRelatedWork W2731899572 @default.
- W4385327857 hasRelatedWork W3116150086 @default.
- W4385327857 hasRelatedWork W3121799932 @default.
- W4385327857 hasRelatedWork W3133861977 @default.
- W4385327857 hasRelatedWork W4200173597 @default.
- W4385327857 hasRelatedWork W4213408743 @default.
- W4385327857 hasRelatedWork W4214796456 @default.
- W4385327857 hasRelatedWork W4287368650 @default.
- W4385327857 hasRelatedWork W4312417841 @default.
- W4385327857 hasRelatedWork W4321369474 @default.
- W4385327857 isParatext "false" @default.
- W4385327857 isRetracted "false" @default.
- W4385327857 workType "article" @default.