Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313443012> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4313443012 endingPage "109286" @default.
- W4313443012 startingPage "109286" @default.
- W4313443012 abstract "Despite the success of deep neural networks, the existence of adversarial attacks has revealed the vulnerability of neural networks in terms of security. Adversarial attacks add subtle noise to the original example, resulting in a false prediction. Although adversarial attacks have been mainly studied in the image domain, a recent line of research has discovered that speech classification systems are also exposed to adversarial attacks. By adding inaudible noise, an adversary can deceive speech classification systems and cause fatal issues in various applications, such as speaker identification and command recognition tasks. However, research on the transferability of audio adversarial examples is still limited. Thus, in this study, we first investigate the transferability of audio adversarial examples with different structures and conditions. Through extensive experiments, we discover that the transferability of audio adversarial examples is related to their noise sensitivity. Based on the analyses, we present a new adversarial attack called noise injected attack that generates highly transferable audio adversarial examples by injecting additive noise during the gradient ascent process. Our experimental results demonstrate that the proposed method outperforms other adversarial attacks in terms of transferability." @default.
- W4313443012 created "2023-01-06" @default.
- W4313443012 creator A5010390242 @default.
- W4313443012 creator A5032839849 @default.
- W4313443012 creator A5056781414 @default.
- W4313443012 date "2023-05-01" @default.
- W4313443012 modified "2023-09-30" @default.
- W4313443012 title "Generating Transferable Adversarial Examples for Speech Classification" @default.
- W4313443012 cites W2997127238 @default.
- W4313443012 cites W3047891567 @default.
- W4313443012 cites W3088377098 @default.
- W4313443012 cites W4247200422 @default.
- W4313443012 cites W821549425 @default.
- W4313443012 doi "https://doi.org/10.1016/j.patcog.2022.109286" @default.
- W4313443012 hasPublicationYear "2023" @default.
- W4313443012 type Work @default.
- W4313443012 citedByCount "1" @default.
- W4313443012 countsByYear W43134430122023 @default.
- W4313443012 crossrefType "journal-article" @default.
- W4313443012 hasAuthorship W4313443012A5010390242 @default.
- W4313443012 hasAuthorship W4313443012A5032839849 @default.
- W4313443012 hasAuthorship W4313443012A5056781414 @default.
- W4313443012 hasConcept C111919701 @default.
- W4313443012 hasConcept C115961682 @default.
- W4313443012 hasConcept C116834253 @default.
- W4313443012 hasConcept C119857082 @default.
- W4313443012 hasConcept C134306372 @default.
- W4313443012 hasConcept C140331021 @default.
- W4313443012 hasConcept C153180895 @default.
- W4313443012 hasConcept C154945302 @default.
- W4313443012 hasConcept C28490314 @default.
- W4313443012 hasConcept C33923547 @default.
- W4313443012 hasConcept C36503486 @default.
- W4313443012 hasConcept C37736160 @default.
- W4313443012 hasConcept C38652104 @default.
- W4313443012 hasConcept C41008148 @default.
- W4313443012 hasConcept C41065033 @default.
- W4313443012 hasConcept C50644808 @default.
- W4313443012 hasConcept C59822182 @default.
- W4313443012 hasConcept C61272859 @default.
- W4313443012 hasConcept C86803240 @default.
- W4313443012 hasConcept C98045186 @default.
- W4313443012 hasConcept C99498987 @default.
- W4313443012 hasConceptScore W4313443012C111919701 @default.
- W4313443012 hasConceptScore W4313443012C115961682 @default.
- W4313443012 hasConceptScore W4313443012C116834253 @default.
- W4313443012 hasConceptScore W4313443012C119857082 @default.
- W4313443012 hasConceptScore W4313443012C134306372 @default.
- W4313443012 hasConceptScore W4313443012C140331021 @default.
- W4313443012 hasConceptScore W4313443012C153180895 @default.
- W4313443012 hasConceptScore W4313443012C154945302 @default.
- W4313443012 hasConceptScore W4313443012C28490314 @default.
- W4313443012 hasConceptScore W4313443012C33923547 @default.
- W4313443012 hasConceptScore W4313443012C36503486 @default.
- W4313443012 hasConceptScore W4313443012C37736160 @default.
- W4313443012 hasConceptScore W4313443012C38652104 @default.
- W4313443012 hasConceptScore W4313443012C41008148 @default.
- W4313443012 hasConceptScore W4313443012C41065033 @default.
- W4313443012 hasConceptScore W4313443012C50644808 @default.
- W4313443012 hasConceptScore W4313443012C59822182 @default.
- W4313443012 hasConceptScore W4313443012C61272859 @default.
- W4313443012 hasConceptScore W4313443012C86803240 @default.
- W4313443012 hasConceptScore W4313443012C98045186 @default.
- W4313443012 hasConceptScore W4313443012C99498987 @default.
- W4313443012 hasFunder F4320322030 @default.
- W4313443012 hasFunder F4320322120 @default.
- W4313443012 hasFunder F4320335489 @default.
- W4313443012 hasLocation W43134430121 @default.
- W4313443012 hasOpenAccess W4313443012 @default.
- W4313443012 hasPrimaryLocation W43134430121 @default.
- W4313443012 hasRelatedWork W2943984343 @default.
- W4313443012 hasRelatedWork W3046843850 @default.
- W4313443012 hasRelatedWork W3085259500 @default.
- W4313443012 hasRelatedWork W3124408655 @default.
- W4313443012 hasRelatedWork W4286761153 @default.
- W4313443012 hasRelatedWork W4293252404 @default.
- W4313443012 hasRelatedWork W4297785512 @default.
- W4313443012 hasRelatedWork W4382318533 @default.
- W4313443012 hasRelatedWork W4382985504 @default.
- W4313443012 hasRelatedWork W4386716251 @default.
- W4313443012 hasVolume "137" @default.
- W4313443012 isParatext "false" @default.
- W4313443012 isRetracted "false" @default.
- W4313443012 workType "article" @default.