Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209551844> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3209551844 endingPage "4358" @default.
- W3209551844 startingPage "4358" @default.
- W3209551844 abstract "Some recent articles have revealed that synthetic aperture radar automatic target recognition (SAR-ATR) models based on deep learning are vulnerable to the attacks of adversarial examples and cause security problems. The adversarial attack can make a deep convolutional neural network (CNN)-based SAR-ATR system output the intended wrong label predictions by adding small adversarial perturbations to the SAR images. The existing optimization-based adversarial attack methods generate adversarial examples by minimizing the mean-squared reconstruction error, causing smooth target edge and blurry weak scattering centers in SAR images. In this paper, we build a UNet-generative adversarial network (GAN) to refine the generation of the SAR-ATR models’ adversarial examples. The UNet learns the separable features of the targets and generates the adversarial examples of SAR images. The GAN makes the generated adversarial examples approximate to real SAR images (with sharp target edge and explicit weak scattering centers) and improves the generation efficiency. We carry out abundant experiments using the proposed adversarial attack algorithm to fool the SAR-ATR models based on several advanced CNNs, which are trained on the measured SAR images of the ground vehicle targets. The quantitative and qualitative results demonstrate the high-quality adversarial example generation and excellent attack effectiveness and efficiency improvement." @default.
- W3209551844 created "2021-11-08" @default.
- W3209551844 creator A5006832020 @default.
- W3209551844 creator A5070576173 @default.
- W3209551844 date "2021-10-29" @default.
- W3209551844 modified "2023-09-26" @default.
- W3209551844 title "Adversarial Attack for SAR Target Recognition Based on UNet-Generative Adversarial Network" @default.
- W3209551844 cites W2038591350 @default.
- W3209551844 cites W2079299474 @default.
- W3209551844 cites W2103290993 @default.
- W3209551844 cites W2148791593 @default.
- W3209551844 cites W2158672843 @default.
- W3209551844 cites W2159582914 @default.
- W3209551844 cites W2292481059 @default.
- W3209551844 cites W2410591237 @default.
- W3209551844 cites W2754361766 @default.
- W3209551844 cites W2789830462 @default.
- W3209551844 cites W2888024549 @default.
- W3209551844 cites W2909390529 @default.
- W3209551844 cites W2917485473 @default.
- W3209551844 cites W3013256492 @default.
- W3209551844 cites W3023942469 @default.
- W3209551844 cites W3035821888 @default.
- W3209551844 cites W3044816028 @default.
- W3209551844 cites W3100144085 @default.
- W3209551844 cites W3108810292 @default.
- W3209551844 cites W3118560043 @default.
- W3209551844 cites W3127159478 @default.
- W3209551844 cites W3127457833 @default.
- W3209551844 cites W3130760752 @default.
- W3209551844 cites W3161293751 @default.
- W3209551844 doi "https://doi.org/10.3390/rs13214358" @default.
- W3209551844 hasPublicationYear "2021" @default.
- W3209551844 type Work @default.
- W3209551844 sameAs 3209551844 @default.
- W3209551844 citedByCount "11" @default.
- W3209551844 countsByYear W32095518442021 @default.
- W3209551844 countsByYear W32095518442022 @default.
- W3209551844 countsByYear W32095518442023 @default.
- W3209551844 crossrefType "journal-article" @default.
- W3209551844 hasAuthorship W3209551844A5006832020 @default.
- W3209551844 hasAuthorship W3209551844A5070576173 @default.
- W3209551844 hasBestOaLocation W32095518441 @default.
- W3209551844 hasConcept C108583219 @default.
- W3209551844 hasConcept C115961682 @default.
- W3209551844 hasConcept C153180895 @default.
- W3209551844 hasConcept C154945302 @default.
- W3209551844 hasConcept C162307627 @default.
- W3209551844 hasConcept C2988773926 @default.
- W3209551844 hasConcept C37736160 @default.
- W3209551844 hasConcept C39890363 @default.
- W3209551844 hasConcept C41008148 @default.
- W3209551844 hasConcept C81363708 @default.
- W3209551844 hasConcept C87360688 @default.
- W3209551844 hasConceptScore W3209551844C108583219 @default.
- W3209551844 hasConceptScore W3209551844C115961682 @default.
- W3209551844 hasConceptScore W3209551844C153180895 @default.
- W3209551844 hasConceptScore W3209551844C154945302 @default.
- W3209551844 hasConceptScore W3209551844C162307627 @default.
- W3209551844 hasConceptScore W3209551844C2988773926 @default.
- W3209551844 hasConceptScore W3209551844C37736160 @default.
- W3209551844 hasConceptScore W3209551844C39890363 @default.
- W3209551844 hasConceptScore W3209551844C41008148 @default.
- W3209551844 hasConceptScore W3209551844C81363708 @default.
- W3209551844 hasConceptScore W3209551844C87360688 @default.
- W3209551844 hasIssue "21" @default.
- W3209551844 hasLocation W32095518441 @default.
- W3209551844 hasLocation W32095518442 @default.
- W3209551844 hasOpenAccess W3209551844 @default.
- W3209551844 hasPrimaryLocation W32095518441 @default.
- W3209551844 hasRelatedWork W2982947611 @default.
- W3209551844 hasRelatedWork W2998996837 @default.
- W3209551844 hasRelatedWork W3024390022 @default.
- W3209551844 hasRelatedWork W3156291593 @default.
- W3209551844 hasRelatedWork W3156786002 @default.
- W3209551844 hasRelatedWork W4200633480 @default.
- W3209551844 hasRelatedWork W4211070796 @default.
- W3209551844 hasRelatedWork W4301431435 @default.
- W3209551844 hasRelatedWork W4367722749 @default.
- W3209551844 hasRelatedWork W4226271949 @default.
- W3209551844 hasVolume "13" @default.
- W3209551844 isParatext "false" @default.
- W3209551844 isRetracted "false" @default.
- W3209551844 magId "3209551844" @default.
- W3209551844 workType "article" @default.