Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315778510> ?p ?o ?g. }
- W4315778510 endingPage "5" @default.
- W4315778510 startingPage "1" @default.
- W4315778510 abstract "Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this paper, we propose a novel generation-network-based approach, called symmetric saliency-based encoder-decoder (SSED), to generate adversarial voice examples to speaker identification. It contains two novel components. First, it uses a novel saliency map decoder to learn the importance of speech samples to the decision of a targeted speaker identification system, so as to make the attacker focus on generating artificial noise to the important samples. It also proposes an angular loss function to push the speaker embedding far away from the source speaker. Our experimental results demonstrate that the proposed SSED yields the state-of-the-art performance, i.e. over 97% targeted attack success rate and a signal-to-noise level of over 39 dB on both the open-set and close-set speaker identification tasks, with a low computational cost." @default.
- W4315778510 created "2023-01-13" @default.
- W4315778510 creator A5016519620 @default.
- W4315778510 creator A5017998597 @default.
- W4315778510 creator A5033532580 @default.
- W4315778510 creator A5070603421 @default.
- W4315778510 creator A5076933423 @default.
- W4315778510 date "2023-01-01" @default.
- W4315778510 modified "2023-10-04" @default.
- W4315778510 title "Symmetric Saliency-Based Adversarial Attack to Speaker Identification" @default.
- W4315778510 cites W2963542245 @default.
- W4315778510 cites W2963857521 @default.
- W4315778510 cites W2969985801 @default.
- W4315778510 cites W2981087920 @default.
- W4315778510 cites W3013020904 @default.
- W4315778510 cites W3015811740 @default.
- W4315778510 cites W3017720918 @default.
- W4315778510 cites W3084424094 @default.
- W4315778510 cites W3095259706 @default.
- W4315778510 cites W3096614974 @default.
- W4315778510 cites W3109668151 @default.
- W4315778510 cites W3128911095 @default.
- W4315778510 cites W3131867595 @default.
- W4315778510 cites W3137249133 @default.
- W4315778510 cites W3153453329 @default.
- W4315778510 cites W3160325739 @default.
- W4315778510 cites W3162158711 @default.
- W4315778510 cites W3204188945 @default.
- W4315778510 cites W3206285027 @default.
- W4315778510 cites W4220961503 @default.
- W4315778510 cites W4283015658 @default.
- W4315778510 cites W4283067891 @default.
- W4315778510 cites W4285094241 @default.
- W4315778510 cites W4285149944 @default.
- W4315778510 doi "https://doi.org/10.1109/lsp.2023.3236509" @default.
- W4315778510 hasPublicationYear "2023" @default.
- W4315778510 type Work @default.
- W4315778510 citedByCount "1" @default.
- W4315778510 countsByYear W43157785102023 @default.
- W4315778510 crossrefType "journal-article" @default.
- W4315778510 hasAuthorship W4315778510A5016519620 @default.
- W4315778510 hasAuthorship W4315778510A5017998597 @default.
- W4315778510 hasAuthorship W4315778510A5033532580 @default.
- W4315778510 hasAuthorship W4315778510A5070603421 @default.
- W4315778510 hasAuthorship W4315778510A5076933423 @default.
- W4315778510 hasBestOaLocation W43157785102 @default.
- W4315778510 hasConcept C115961682 @default.
- W4315778510 hasConcept C116834253 @default.
- W4315778510 hasConcept C120665830 @default.
- W4315778510 hasConcept C121332964 @default.
- W4315778510 hasConcept C133892786 @default.
- W4315778510 hasConcept C149838564 @default.
- W4315778510 hasConcept C153180895 @default.
- W4315778510 hasConcept C154945302 @default.
- W4315778510 hasConcept C177264268 @default.
- W4315778510 hasConcept C192209626 @default.
- W4315778510 hasConcept C199360897 @default.
- W4315778510 hasConcept C28490314 @default.
- W4315778510 hasConcept C2986627078 @default.
- W4315778510 hasConcept C37736160 @default.
- W4315778510 hasConcept C41008148 @default.
- W4315778510 hasConcept C41608201 @default.
- W4315778510 hasConcept C59822182 @default.
- W4315778510 hasConcept C86803240 @default.
- W4315778510 hasConcept C99498987 @default.
- W4315778510 hasConceptScore W4315778510C115961682 @default.
- W4315778510 hasConceptScore W4315778510C116834253 @default.
- W4315778510 hasConceptScore W4315778510C120665830 @default.
- W4315778510 hasConceptScore W4315778510C121332964 @default.
- W4315778510 hasConceptScore W4315778510C133892786 @default.
- W4315778510 hasConceptScore W4315778510C149838564 @default.
- W4315778510 hasConceptScore W4315778510C153180895 @default.
- W4315778510 hasConceptScore W4315778510C154945302 @default.
- W4315778510 hasConceptScore W4315778510C177264268 @default.
- W4315778510 hasConceptScore W4315778510C192209626 @default.
- W4315778510 hasConceptScore W4315778510C199360897 @default.
- W4315778510 hasConceptScore W4315778510C28490314 @default.
- W4315778510 hasConceptScore W4315778510C2986627078 @default.
- W4315778510 hasConceptScore W4315778510C37736160 @default.
- W4315778510 hasConceptScore W4315778510C41008148 @default.
- W4315778510 hasConceptScore W4315778510C41608201 @default.
- W4315778510 hasConceptScore W4315778510C59822182 @default.
- W4315778510 hasConceptScore W4315778510C86803240 @default.
- W4315778510 hasConceptScore W4315778510C99498987 @default.
- W4315778510 hasFunder F4320321001 @default.
- W4315778510 hasLocation W43157785101 @default.
- W4315778510 hasLocation W43157785102 @default.
- W4315778510 hasLocation W43157785103 @default.
- W4315778510 hasOpenAccess W4315778510 @default.
- W4315778510 hasPrimaryLocation W43157785101 @default.
- W4315778510 hasRelatedWork W1521049138 @default.
- W4315778510 hasRelatedWork W1843883989 @default.
- W4315778510 hasRelatedWork W1946464671 @default.
- W4315778510 hasRelatedWork W1973693762 @default.
- W4315778510 hasRelatedWork W2087341511 @default.
- W4315778510 hasRelatedWork W2126085626 @default.
- W4315778510 hasRelatedWork W2249138175 @default.
- W4315778510 hasRelatedWork W2378903289 @default.