Matches in SemOpenAlex for { <https://semopenalex.org/work/W3193088178> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3193088178 abstract "Deep Neural Networks have been shown to be vulnerable to various kinds of adversarial perturbations. In addition to widely studied additive noise based perturbations, adversarial examples can also be created by applying a per pixel spatial drift on input images. While spatial transformation based adversarial examples look more natural to human observers due to absence of additive noise, they still possess visible distortions caused by spatial transformations. Since the human vision is more sensitive to the distortions in the luminance compared to those in chrominance channels, which is one of the main ideas behind the lossy visual multimedia compression standards, we propose a spatial transformation based perturbation method to create adversarial examples by only modifying the color components of an input image. While having competitive fooling rates on CIFAR-10 and NIPS2017 Adversarial Learning Challenge datasets, examples created with the proposed method have better scores with regards to various perceptual quality metrics. Human visual perception studies validate that the examples are more natural looking and often indistinguishable from their original counterparts." @default.
- W3193088178 created "2021-08-16" @default.
- W3193088178 creator A5001883356 @default.
- W3193088178 creator A5003028527 @default.
- W3193088178 creator A5047433939 @default.
- W3193088178 creator A5056400663 @default.
- W3193088178 creator A5081326390 @default.
- W3193088178 date "2021-10-20" @default.
- W3193088178 modified "2023-10-16" @default.
- W3193088178 title "Imperceptible Adversarial Examples by Spatial Chroma-Shift" @default.
- W3193088178 cites W1993806408 @default.
- W3193088178 cites W2097117768 @default.
- W3193088178 cites W2150969685 @default.
- W3193088178 cites W2194775991 @default.
- W3193088178 cites W2243397390 @default.
- W3193088178 cites W2348664362 @default.
- W3193088178 cites W2543927648 @default.
- W3193088178 cites W2774644650 @default.
- W3193088178 cites W2883718552 @default.
- W3193088178 cites W2962785568 @default.
- W3193088178 cites W2963098487 @default.
- W3193088178 cites W2963857521 @default.
- W3193088178 cites W3034196143 @default.
- W3193088178 cites W3034412497 @default.
- W3193088178 cites W3123981332 @default.
- W3193088178 doi "https://doi.org/10.1145/3475724.3483604" @default.
- W3193088178 hasPublicationYear "2021" @default.
- W3193088178 type Work @default.
- W3193088178 sameAs 3193088178 @default.
- W3193088178 citedByCount "5" @default.
- W3193088178 countsByYear W31930881782022 @default.
- W3193088178 countsByYear W31930881782023 @default.
- W3193088178 crossrefType "proceedings-article" @default.
- W3193088178 hasAuthorship W3193088178A5001883356 @default.
- W3193088178 hasAuthorship W3193088178A5003028527 @default.
- W3193088178 hasAuthorship W3193088178A5047433939 @default.
- W3193088178 hasAuthorship W3193088178A5056400663 @default.
- W3193088178 hasAuthorship W3193088178A5081326390 @default.
- W3193088178 hasBestOaLocation W31930881782 @default.
- W3193088178 hasConcept C104317684 @default.
- W3193088178 hasConcept C115961682 @default.
- W3193088178 hasConcept C11727466 @default.
- W3193088178 hasConcept C154945302 @default.
- W3193088178 hasConcept C160086991 @default.
- W3193088178 hasConcept C160633673 @default.
- W3193088178 hasConcept C163204269 @default.
- W3193088178 hasConcept C165021410 @default.
- W3193088178 hasConcept C169760540 @default.
- W3193088178 hasConcept C185592680 @default.
- W3193088178 hasConcept C204241405 @default.
- W3193088178 hasConcept C26760741 @default.
- W3193088178 hasConcept C31972630 @default.
- W3193088178 hasConcept C37736160 @default.
- W3193088178 hasConcept C41008148 @default.
- W3193088178 hasConcept C55493867 @default.
- W3193088178 hasConcept C73313986 @default.
- W3193088178 hasConcept C86803240 @default.
- W3193088178 hasConceptScore W3193088178C104317684 @default.
- W3193088178 hasConceptScore W3193088178C115961682 @default.
- W3193088178 hasConceptScore W3193088178C11727466 @default.
- W3193088178 hasConceptScore W3193088178C154945302 @default.
- W3193088178 hasConceptScore W3193088178C160086991 @default.
- W3193088178 hasConceptScore W3193088178C160633673 @default.
- W3193088178 hasConceptScore W3193088178C163204269 @default.
- W3193088178 hasConceptScore W3193088178C165021410 @default.
- W3193088178 hasConceptScore W3193088178C169760540 @default.
- W3193088178 hasConceptScore W3193088178C185592680 @default.
- W3193088178 hasConceptScore W3193088178C204241405 @default.
- W3193088178 hasConceptScore W3193088178C26760741 @default.
- W3193088178 hasConceptScore W3193088178C31972630 @default.
- W3193088178 hasConceptScore W3193088178C37736160 @default.
- W3193088178 hasConceptScore W3193088178C41008148 @default.
- W3193088178 hasConceptScore W3193088178C55493867 @default.
- W3193088178 hasConceptScore W3193088178C73313986 @default.
- W3193088178 hasConceptScore W3193088178C86803240 @default.
- W3193088178 hasLocation W31930881781 @default.
- W3193088178 hasLocation W31930881782 @default.
- W3193088178 hasLocation W31930881783 @default.
- W3193088178 hasOpenAccess W3193088178 @default.
- W3193088178 hasPrimaryLocation W31930881781 @default.
- W3193088178 hasRelatedWork W1574999717 @default.
- W3193088178 hasRelatedWork W166251047 @default.
- W3193088178 hasRelatedWork W2020564930 @default.
- W3193088178 hasRelatedWork W2041408572 @default.
- W3193088178 hasRelatedWork W2059339452 @default.
- W3193088178 hasRelatedWork W2126841226 @default.
- W3193088178 hasRelatedWork W2236660010 @default.
- W3193088178 hasRelatedWork W2262668847 @default.
- W3193088178 hasRelatedWork W2370766994 @default.
- W3193088178 hasRelatedWork W2995115364 @default.
- W3193088178 isParatext "false" @default.
- W3193088178 isRetracted "false" @default.
- W3193088178 magId "3193088178" @default.
- W3193088178 workType "article" @default.