Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310346645> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4310346645 endingPage "360" @default.
- W4310346645 startingPage "351" @default.
- W4310346645 abstract "With deep learning models been widely applied to SAR images interpretation, the adversarial robustness problem of models has drawn much attention. Due to the application in military fields, SAR image processing have extremely requirements on security. However, the popular optimized adversarial perturbation algorithms calculated the perturbation for one single image at a time, thus cannot be adapted to real-time adversarial scenarios. Also, the perturbation is designed in full digital space and lacks of sematic information of the targets. Faced with those problems, this paper proposes a SAR universal adversarial perturbation (SAR-UAP) for SAR images adversarial attacks based on template-based lightweight generative model without discriminator. The model has simple structure which consists of six convolutional layers and uses the fixed template as the input of the generator. Template-based UAP ensures that once training is finished, the disturbances remain unchanged in spite of the changing of images chosen to attack. Model performance was tested on the MSTAR dataset for eight classical CNNs. Compared with other GAN-based UAP methods, SAR-UAP gained slightly higher fooling rate which is over 85%, while the illustration showed SAR-UAP are much more target-focused. The transferability of perturbation was also verified." @default.
- W4310346645 created "2022-12-09" @default.
- W4310346645 creator A5015131366 @default.
- W4310346645 creator A5026265793 @default.
- W4310346645 creator A5082887216 @default.
- W4310346645 date "2022-11-30" @default.
- W4310346645 modified "2023-10-14" @default.
- W4310346645 title "Template-Based Universal Adversarial Perturbation for SAR Target Classification" @default.
- W4310346645 cites W2543927648 @default.
- W4310346645 cites W2963560523 @default.
- W4310346645 cites W2963809642 @default.
- W4310346645 cites W2963857521 @default.
- W4310346645 cites W3013256492 @default.
- W4310346645 cites W3100144085 @default.
- W4310346645 cites W3104218734 @default.
- W4310346645 cites W3207962952 @default.
- W4310346645 cites W3209551844 @default.
- W4310346645 doi "https://doi.org/10.1007/978-981-19-8202-6_32" @default.
- W4310346645 hasPublicationYear "2022" @default.
- W4310346645 type Work @default.
- W4310346645 citedByCount "0" @default.
- W4310346645 crossrefType "book-chapter" @default.
- W4310346645 hasAuthorship W4310346645A5015131366 @default.
- W4310346645 hasAuthorship W4310346645A5026265793 @default.
- W4310346645 hasAuthorship W4310346645A5082887216 @default.
- W4310346645 hasConcept C119857082 @default.
- W4310346645 hasConcept C121332964 @default.
- W4310346645 hasConcept C140331021 @default.
- W4310346645 hasConcept C153180895 @default.
- W4310346645 hasConcept C154945302 @default.
- W4310346645 hasConcept C177918212 @default.
- W4310346645 hasConcept C2779803651 @default.
- W4310346645 hasConcept C31972630 @default.
- W4310346645 hasConcept C37736160 @default.
- W4310346645 hasConcept C41008148 @default.
- W4310346645 hasConcept C61272859 @default.
- W4310346645 hasConcept C62520636 @default.
- W4310346645 hasConcept C76155785 @default.
- W4310346645 hasConcept C87360688 @default.
- W4310346645 hasConcept C94915269 @default.
- W4310346645 hasConceptScore W4310346645C119857082 @default.
- W4310346645 hasConceptScore W4310346645C121332964 @default.
- W4310346645 hasConceptScore W4310346645C140331021 @default.
- W4310346645 hasConceptScore W4310346645C153180895 @default.
- W4310346645 hasConceptScore W4310346645C154945302 @default.
- W4310346645 hasConceptScore W4310346645C177918212 @default.
- W4310346645 hasConceptScore W4310346645C2779803651 @default.
- W4310346645 hasConceptScore W4310346645C31972630 @default.
- W4310346645 hasConceptScore W4310346645C37736160 @default.
- W4310346645 hasConceptScore W4310346645C41008148 @default.
- W4310346645 hasConceptScore W4310346645C61272859 @default.
- W4310346645 hasConceptScore W4310346645C62520636 @default.
- W4310346645 hasConceptScore W4310346645C76155785 @default.
- W4310346645 hasConceptScore W4310346645C87360688 @default.
- W4310346645 hasConceptScore W4310346645C94915269 @default.
- W4310346645 hasLocation W43103466451 @default.
- W4310346645 hasOpenAccess W4310346645 @default.
- W4310346645 hasPrimaryLocation W43103466451 @default.
- W4310346645 hasRelatedWork W1964120219 @default.
- W4310346645 hasRelatedWork W2115641108 @default.
- W4310346645 hasRelatedWork W2543161807 @default.
- W4310346645 hasRelatedWork W2949849531 @default.
- W4310346645 hasRelatedWork W2973417394 @default.
- W4310346645 hasRelatedWork W4280544492 @default.
- W4310346645 hasRelatedWork W4283772777 @default.
- W4310346645 hasRelatedWork W4310346645 @default.
- W4310346645 hasRelatedWork W4312963184 @default.
- W4310346645 hasRelatedWork W4367190582 @default.
- W4310346645 isParatext "false" @default.
- W4310346645 isRetracted "false" @default.
- W4310346645 workType "book-chapter" @default.