Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310989084> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4310989084 abstract "This paper proposes PatternAttack to mitigate two major issues of Adversarial Transformation Network (ATN) including the low diversity and the low quality of adversarial examples. In order to deal with the first issue, this research proposes a stacked convolutional autoencoder based on patterns to generalize ATN. This proposed autoencoder could support different patterns such as all-pixel pattern, object boundary pattern, and class model map pattern. In order to deal with the second issue, this paper presents an algorithm to improve the quality of adversarial examples in terms of $$L_0$$ -norm and $$L_2$$ -norm. This algorithm employs adversarial pixel ranking heuristics such as JSMA and COI to prioritize adversarial pixels. To demonstrate the advantages of the proposed method, comprehensive experiments have been conducted on the MNIST dataset and the CIFAR-10 dataset. For the first issue, the proposed autoencoder generates diverse adversarial examples. For the second issue, the proposed algorithm significantly improves the quality of adversarial examples. In terms of $$L_0$$ -norm, the proposed algorithm decreases from hundreds of adversarial pixels to one adversarial pixel. In terms of $$L_2$$ -norm, the proposed algorithm reduces the average distance considerably. These results show that the proposed method can generate high-quality and diverse adversarial examples in practice." @default.
- W4310989084 created "2022-12-22" @default.
- W4310989084 creator A5020815082 @default.
- W4310989084 creator A5027582055 @default.
- W4310989084 creator A5055308912 @default.
- W4310989084 creator A5077641909 @default.
- W4310989084 creator A5079840241 @default.
- W4310989084 date "2022-11-29" @default.
- W4310989084 modified "2023-10-18" @default.
- W4310989084 title "Improving diversity and quality of adversarial examples in adversarial transformation network" @default.
- W4310989084 cites W1849277567 @default.
- W4310989084 cites W2112796928 @default.
- W4310989084 cites W2136655611 @default.
- W4310989084 cites W2180612164 @default.
- W4310989084 cites W2221625691 @default.
- W4310989084 cites W2243397390 @default.
- W4310989084 cites W2503388974 @default.
- W4310989084 cites W2616028256 @default.
- W4310989084 cites W2618530766 @default.
- W4310989084 cites W2774644650 @default.
- W4310989084 cites W2781800156 @default.
- W4310989084 cites W2952813363 @default.
- W4310989084 cites W2954252370 @default.
- W4310989084 cites W2963857521 @default.
- W4310989084 cites W3013135147 @default.
- W4310989084 cites W3101609372 @default.
- W4310989084 cites W3200113267 @default.
- W4310989084 cites W3211999566 @default.
- W4310989084 cites W4293060235 @default.
- W4310989084 doi "https://doi.org/10.1007/s00500-022-07655-y" @default.
- W4310989084 hasPublicationYear "2022" @default.
- W4310989084 type Work @default.
- W4310989084 citedByCount "0" @default.
- W4310989084 crossrefType "journal-article" @default.
- W4310989084 hasAuthorship W4310989084A5020815082 @default.
- W4310989084 hasAuthorship W4310989084A5027582055 @default.
- W4310989084 hasAuthorship W4310989084A5055308912 @default.
- W4310989084 hasAuthorship W4310989084A5077641909 @default.
- W4310989084 hasAuthorship W4310989084A5079840241 @default.
- W4310989084 hasBestOaLocation W43109890842 @default.
- W4310989084 hasConcept C101738243 @default.
- W4310989084 hasConcept C108583219 @default.
- W4310989084 hasConcept C111919701 @default.
- W4310989084 hasConcept C11413529 @default.
- W4310989084 hasConcept C119857082 @default.
- W4310989084 hasConcept C127705205 @default.
- W4310989084 hasConcept C153180895 @default.
- W4310989084 hasConcept C154945302 @default.
- W4310989084 hasConcept C160633673 @default.
- W4310989084 hasConcept C17744445 @default.
- W4310989084 hasConcept C190502265 @default.
- W4310989084 hasConcept C191795146 @default.
- W4310989084 hasConcept C199539241 @default.
- W4310989084 hasConcept C37736160 @default.
- W4310989084 hasConcept C41008148 @default.
- W4310989084 hasConceptScore W4310989084C101738243 @default.
- W4310989084 hasConceptScore W4310989084C108583219 @default.
- W4310989084 hasConceptScore W4310989084C111919701 @default.
- W4310989084 hasConceptScore W4310989084C11413529 @default.
- W4310989084 hasConceptScore W4310989084C119857082 @default.
- W4310989084 hasConceptScore W4310989084C127705205 @default.
- W4310989084 hasConceptScore W4310989084C153180895 @default.
- W4310989084 hasConceptScore W4310989084C154945302 @default.
- W4310989084 hasConceptScore W4310989084C160633673 @default.
- W4310989084 hasConceptScore W4310989084C17744445 @default.
- W4310989084 hasConceptScore W4310989084C190502265 @default.
- W4310989084 hasConceptScore W4310989084C191795146 @default.
- W4310989084 hasConceptScore W4310989084C199539241 @default.
- W4310989084 hasConceptScore W4310989084C37736160 @default.
- W4310989084 hasConceptScore W4310989084C41008148 @default.
- W4310989084 hasFunder F4320328994 @default.
- W4310989084 hasLocation W43109890841 @default.
- W4310989084 hasLocation W43109890842 @default.
- W4310989084 hasOpenAccess W4310989084 @default.
- W4310989084 hasPrimaryLocation W43109890841 @default.
- W4310989084 hasRelatedWork W2597787948 @default.
- W4310989084 hasRelatedWork W2766433866 @default.
- W4310989084 hasRelatedWork W2951786554 @default.
- W4310989084 hasRelatedWork W3013699911 @default.
- W4310989084 hasRelatedWork W3044458868 @default.
- W4310989084 hasRelatedWork W3120206105 @default.
- W4310989084 hasRelatedWork W4213225422 @default.
- W4310989084 hasRelatedWork W4220775285 @default.
- W4310989084 hasRelatedWork W4287637979 @default.
- W4310989084 hasRelatedWork W4293054861 @default.
- W4310989084 isParatext "false" @default.
- W4310989084 isRetracted "false" @default.
- W4310989084 workType "article" @default.