Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133938492> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3133938492 endingPage "428" @default.
- W3133938492 startingPage "428" @default.
- W3133938492 abstract "This paper presents research focusing on visualization and pattern recognition based on computer science. Although deep neural networks demonstrate satisfactory performance regarding image and voice recognition, as well as pattern analysis and intrusion detection, they exhibit inferior performance towards adversarial examples. Noise introduction, to some degree, to the original data could lead adversarial examples to be misclassified by deep neural networks, even though they can still be deemed as normal by humans. In this paper, a robust diversity adversarial training method against adversarial attacks was demonstrated. In this approach, the target model is more robust to unknown adversarial examples, as it trains various adversarial samples. During the experiment, Tensorflow was employed as our deep learning framework, while MNIST and Fashion-MNIST were used as experimental datasets. Results revealed that the diversity training method has lowered the attack success rate by an average of 27.2 and 24.3% for various adversarial examples, while maintaining the 98.7 and 91.5% accuracy rates regarding the original data of MNIST and Fashion-MNIST." @default.
- W3133938492 created "2021-03-15" @default.
- W3133938492 creator A5040423887 @default.
- W3133938492 creator A5077437724 @default.
- W3133938492 date "2021-03-06" @default.
- W3133938492 modified "2023-10-06" @default.
- W3133938492 title "Diversity Adversarial Training against Adversarial Attack on Deep Neural Networks" @default.
- W3133938492 cites W2076063813 @default.
- W3133938492 cites W2112796928 @default.
- W3133938492 cites W2125908420 @default.
- W3133938492 cites W2406556600 @default.
- W3133938492 cites W2893838482 @default.
- W3133938492 cites W2904294250 @default.
- W3133938492 cites W2944145386 @default.
- W3133938492 cites W2960924414 @default.
- W3133938492 cites W2963739340 @default.
- W3133938492 cites W3014697957 @default.
- W3133938492 cites W3025953162 @default.
- W3133938492 cites W3036436580 @default.
- W3133938492 cites W3081785824 @default.
- W3133938492 cites W3093748630 @default.
- W3133938492 cites W3094138545 @default.
- W3133938492 cites W3113061480 @default.
- W3133938492 doi "https://doi.org/10.3390/sym13030428" @default.
- W3133938492 hasPublicationYear "2021" @default.
- W3133938492 type Work @default.
- W3133938492 sameAs 3133938492 @default.
- W3133938492 citedByCount "10" @default.
- W3133938492 countsByYear W31339384922021 @default.
- W3133938492 countsByYear W31339384922022 @default.
- W3133938492 countsByYear W31339384922023 @default.
- W3133938492 crossrefType "journal-article" @default.
- W3133938492 hasAuthorship W3133938492A5040423887 @default.
- W3133938492 hasAuthorship W3133938492A5077437724 @default.
- W3133938492 hasBestOaLocation W31339384921 @default.
- W3133938492 hasConcept C108583219 @default.
- W3133938492 hasConcept C115961682 @default.
- W3133938492 hasConcept C119857082 @default.
- W3133938492 hasConcept C144024400 @default.
- W3133938492 hasConcept C153180895 @default.
- W3133938492 hasConcept C154945302 @default.
- W3133938492 hasConcept C190502265 @default.
- W3133938492 hasConcept C19165224 @default.
- W3133938492 hasConcept C2781316041 @default.
- W3133938492 hasConcept C2984842247 @default.
- W3133938492 hasConcept C36464697 @default.
- W3133938492 hasConcept C37736160 @default.
- W3133938492 hasConcept C41008148 @default.
- W3133938492 hasConcept C50644808 @default.
- W3133938492 hasConceptScore W3133938492C108583219 @default.
- W3133938492 hasConceptScore W3133938492C115961682 @default.
- W3133938492 hasConceptScore W3133938492C119857082 @default.
- W3133938492 hasConceptScore W3133938492C144024400 @default.
- W3133938492 hasConceptScore W3133938492C153180895 @default.
- W3133938492 hasConceptScore W3133938492C154945302 @default.
- W3133938492 hasConceptScore W3133938492C190502265 @default.
- W3133938492 hasConceptScore W3133938492C19165224 @default.
- W3133938492 hasConceptScore W3133938492C2781316041 @default.
- W3133938492 hasConceptScore W3133938492C2984842247 @default.
- W3133938492 hasConceptScore W3133938492C36464697 @default.
- W3133938492 hasConceptScore W3133938492C37736160 @default.
- W3133938492 hasConceptScore W3133938492C41008148 @default.
- W3133938492 hasConceptScore W3133938492C50644808 @default.
- W3133938492 hasIssue "3" @default.
- W3133938492 hasLocation W31339384921 @default.
- W3133938492 hasOpenAccess W3133938492 @default.
- W3133938492 hasPrimaryLocation W31339384921 @default.
- W3133938492 hasRelatedWork W2597787948 @default.
- W3133938492 hasRelatedWork W2897842727 @default.
- W3133938492 hasRelatedWork W2908634608 @default.
- W3133938492 hasRelatedWork W2947175736 @default.
- W3133938492 hasRelatedWork W3139282803 @default.
- W3133938492 hasRelatedWork W3208723233 @default.
- W3133938492 hasRelatedWork W4200110354 @default.
- W3133938492 hasRelatedWork W4220691143 @default.
- W3133938492 hasRelatedWork W4288639242 @default.
- W3133938492 hasRelatedWork W4293054861 @default.
- W3133938492 hasVolume "13" @default.
- W3133938492 isParatext "false" @default.
- W3133938492 isRetracted "false" @default.
- W3133938492 magId "3133938492" @default.
- W3133938492 workType "article" @default.