FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100144085> ?p ?o ?g. }

• W3100144085 endingPage "1347" @default.
• W3100144085 startingPage "1333" @default.
• W3100144085 abstract "Synthetic aperture radar (SAR) has all-day and all-weather characteristics and plays an extremely important role in the military field. The breakthroughs in deep learning methods represented by convolutional neural network (CNN) models have greatly improved the SAR image recognition accuracy. Classification models based on CNNs can perform high-precision classification, but there are security problems against adversarial examples (AEs). However, the research on AEs is mostly limited to natural images, and remote sensing images (SAR, multispectral, etc.) have not been extensively studied. To explore the basic characteristics of AEs of SAR images (ASIs), we use two classic white-box attack methods to generate ASIs from two SAR image classification datasets and then evaluate the vulnerability of six commonly used CNNs. The results show that ASIs are quite effective in fooling CNNs trained on SAR images, as indicated by the obtained high attack success rate. Due to the structural differences among CNNs, different CNNs present different vulnerabilities in the face of ASIs. We found that ASIs generated by nontarget attack algorithms feature attack selectivity, which is related to the feature space distribution of the original SAR images and the decision boundary of the classification model. We propose the sample-boundary-based AE selectivity distance to successfully explain the attack selectivity of ASIs. We also analyze the effects of image parameters, such as image size and number of channels, on the attack success rate of ASIs through parameter sensitivity. The experimental results of this study provide data support and an effective reference for attacks on and the defense capabilities of various CNNs with regard to AEs in SAR image classification models." @default.
• W3100144085 created "2020-11-23" @default.
• W3100144085 creator A5003271251 @default.
• W3100144085 creator A5007291380 @default.
• W3100144085 creator A5020005878 @default.
• W3100144085 creator A5030897972 @default.
• W3100144085 creator A5047373240 @default.
• W3100144085 creator A5051332435 @default.
• W3100144085 creator A5059100653 @default.
• W3100144085 creator A5070131811 @default.
• W3100144085 date "2021-01-01" @default.
• W3100144085 modified "2023-10-13" @default.
• W3100144085 title "Adversarial Examples for CNN-Based SAR Image Classification: An Experience Study" @default.
• W3100144085 cites W1696131234 @default.
• W3100144085 cites W1932198206 @default.
• W3100144085 cites W1964166023 @default.
• W3100144085 cites W2060824061 @default.
• W3100144085 cites W2091823356 @default.
• W3100144085 cites W2097117768 @default.
• W3100144085 cites W2113622856 @default.
• W3100144085 cites W2180612164 @default.
• W3100144085 cites W2183341477 @default.
• W3100144085 cites W2194775991 @default.
• W3100144085 cites W2243397390 @default.
• W3100144085 cites W2289855966 @default.
• W3100144085 cites W2517475170 @default.
• W3100144085 cites W2523772278 @default.
• W3100144085 cites W2543927648 @default.
• W3100144085 cites W2549139847 @default.
• W3100144085 cites W2613825824 @default.
• W3100144085 cites W2773879941 @default.
• W3100144085 cites W2800744393 @default.
• W3100144085 cites W2805508018 @default.
• W3100144085 cites W2810454813 @default.
• W3100144085 cites W2895222021 @default.
• W3100144085 cites W2896903403 @default.
• W3100144085 cites W2945035621 @default.
• W3100144085 cites W2949128310 @default.
• W3100144085 cites W2960586030 @default.
• W3100144085 cites W2962718684 @default.
• W3100144085 cites W2963149332 @default.
• W3100144085 cites W2963178695 @default.
• W3100144085 cites W2963229629 @default.
• W3100144085 cites W2963446712 @default.
• W3100144085 cites W2963448658 @default.
• W3100144085 cites W2963857521 @default.
• W3100144085 cites W2964097310 @default.
• W3100144085 cites W2964301649 @default.
• W3100144085 cites W2965333252 @default.
• W3100144085 cites W2967731069 @default.
• W3100144085 cites W2970255644 @default.
• W3100144085 cites W3103557498 @default.
• W3100144085 cites W3104355817 @default.
• W3100144085 cites W3105806188 @default.
• W3100144085 cites W4205805299 @default.
• W3100144085 doi "https://doi.org/10.1109/jstars.2020.3038683" @default.
• W3100144085 hasPublicationYear "2021" @default.
• W3100144085 type Work @default.
• W3100144085 sameAs 3100144085 @default.
• W3100144085 citedByCount "34" @default.
• W3100144085 countsByYear W31001440852021 @default.
• W3100144085 countsByYear W31001440852022 @default.
• W3100144085 countsByYear W31001440852023 @default.
• W3100144085 crossrefType "journal-article" @default.
• W3100144085 hasAuthorship W3100144085A5003271251 @default.
• W3100144085 hasAuthorship W3100144085A5007291380 @default.
• W3100144085 hasAuthorship W3100144085A5020005878 @default.
• W3100144085 hasAuthorship W3100144085A5030897972 @default.
• W3100144085 hasAuthorship W3100144085A5047373240 @default.
• W3100144085 hasAuthorship W3100144085A5051332435 @default.
• W3100144085 hasAuthorship W3100144085A5059100653 @default.
• W3100144085 hasAuthorship W3100144085A5070131811 @default.
• W3100144085 hasBestOaLocation W31001440851 @default.
• W3100144085 hasConcept C108583219 @default.
• W3100144085 hasConcept C115961682 @default.
• W3100144085 hasConcept C119857082 @default.
• W3100144085 hasConcept C138885662 @default.
• W3100144085 hasConcept C153180895 @default.
• W3100144085 hasConcept C154945302 @default.
• W3100144085 hasConcept C173163844 @default.
• W3100144085 hasConcept C2776401178 @default.
• W3100144085 hasConcept C41008148 @default.
• W3100144085 hasConcept C41895202 @default.
• W3100144085 hasConcept C52622490 @default.
• W3100144085 hasConcept C75294576 @default.
• W3100144085 hasConcept C81363708 @default.
• W3100144085 hasConcept C83665646 @default.
• W3100144085 hasConcept C87360688 @default.
• W3100144085 hasConceptScore W3100144085C108583219 @default.
• W3100144085 hasConceptScore W3100144085C115961682 @default.
• W3100144085 hasConceptScore W3100144085C119857082 @default.
• W3100144085 hasConceptScore W3100144085C138885662 @default.
• W3100144085 hasConceptScore W3100144085C153180895 @default.
• W3100144085 hasConceptScore W3100144085C154945302 @default.
• W3100144085 hasConceptScore W3100144085C173163844 @default.
• W3100144085 hasConceptScore W3100144085C2776401178 @default.
• W3100144085 hasConceptScore W3100144085C41008148 @default.
• W3100144085 hasConceptScore W3100144085C41895202 @default.

• next