Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310825102> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4310825102 abstract "The success of deep learning is partly attributed to the availability of massive data downloaded freely from the Internet. However, it also means that users' private data may be collected by commercial organizations without consent and used to train their models. Therefore, it's important and necessary to develop a method or tool to prevent unauthorized data exploitation. In this paper, we propose ConfounderGAN, a generative adversarial network (GAN) that can make personal image data unlearnable to protect the data privacy of its owners. Specifically, the noise produced by the generator for each image has the confounder property. It can build spurious correlations between images and labels, so that the model cannot learn the correct mapping from images to labels in this noise-added dataset. Meanwhile, the discriminator is used to ensure that the generated noise is small and imperceptible, thereby remaining the normal utility of the encrypted image for humans. The experiments are conducted in six image classification datasets, consisting of three natural object datasets and three medical datasets. The results demonstrate that our method not only outperforms state-of-the-art methods in standard settings, but can also be applied to fast encryption scenarios. Moreover, we show a series of transferability and stability experiments to further illustrate the effectiveness and superiority of our method." @default.
- W4310825102 created "2022-12-18" @default.
- W4310825102 creator A5024076883 @default.
- W4310825102 creator A5026553094 @default.
- W4310825102 creator A5041727387 @default.
- W4310825102 creator A5047455588 @default.
- W4310825102 creator A5070320567 @default.
- W4310825102 creator A5090690232 @default.
- W4310825102 date "2022-12-04" @default.
- W4310825102 modified "2023-10-10" @default.
- W4310825102 title "ConfounderGAN: Protecting Image Data Privacy with Causal Confounder" @default.
- W4310825102 doi "https://doi.org/10.48550/arxiv.2212.01767" @default.
- W4310825102 hasPublicationYear "2022" @default.
- W4310825102 type Work @default.
- W4310825102 citedByCount "0" @default.
- W4310825102 crossrefType "posted-content" @default.
- W4310825102 hasAuthorship W4310825102A5024076883 @default.
- W4310825102 hasAuthorship W4310825102A5026553094 @default.
- W4310825102 hasAuthorship W4310825102A5041727387 @default.
- W4310825102 hasAuthorship W4310825102A5047455588 @default.
- W4310825102 hasAuthorship W4310825102A5070320567 @default.
- W4310825102 hasAuthorship W4310825102A5090690232 @default.
- W4310825102 hasBestOaLocation W43108251021 @default.
- W4310825102 hasConcept C111472728 @default.
- W4310825102 hasConcept C115961682 @default.
- W4310825102 hasConcept C119857082 @default.
- W4310825102 hasConcept C121332964 @default.
- W4310825102 hasConcept C124101348 @default.
- W4310825102 hasConcept C138885662 @default.
- W4310825102 hasConcept C148730421 @default.
- W4310825102 hasConcept C154945302 @default.
- W4310825102 hasConcept C163258240 @default.
- W4310825102 hasConcept C189950617 @default.
- W4310825102 hasConcept C2779803651 @default.
- W4310825102 hasConcept C2780992000 @default.
- W4310825102 hasConcept C38652104 @default.
- W4310825102 hasConcept C41008148 @default.
- W4310825102 hasConcept C62520636 @default.
- W4310825102 hasConcept C76155785 @default.
- W4310825102 hasConcept C94915269 @default.
- W4310825102 hasConcept C97256817 @default.
- W4310825102 hasConcept C99498987 @default.
- W4310825102 hasConceptScore W4310825102C111472728 @default.
- W4310825102 hasConceptScore W4310825102C115961682 @default.
- W4310825102 hasConceptScore W4310825102C119857082 @default.
- W4310825102 hasConceptScore W4310825102C121332964 @default.
- W4310825102 hasConceptScore W4310825102C124101348 @default.
- W4310825102 hasConceptScore W4310825102C138885662 @default.
- W4310825102 hasConceptScore W4310825102C148730421 @default.
- W4310825102 hasConceptScore W4310825102C154945302 @default.
- W4310825102 hasConceptScore W4310825102C163258240 @default.
- W4310825102 hasConceptScore W4310825102C189950617 @default.
- W4310825102 hasConceptScore W4310825102C2779803651 @default.
- W4310825102 hasConceptScore W4310825102C2780992000 @default.
- W4310825102 hasConceptScore W4310825102C38652104 @default.
- W4310825102 hasConceptScore W4310825102C41008148 @default.
- W4310825102 hasConceptScore W4310825102C62520636 @default.
- W4310825102 hasConceptScore W4310825102C76155785 @default.
- W4310825102 hasConceptScore W4310825102C94915269 @default.
- W4310825102 hasConceptScore W4310825102C97256817 @default.
- W4310825102 hasConceptScore W4310825102C99498987 @default.
- W4310825102 hasLocation W43108251021 @default.
- W4310825102 hasLocation W43108251022 @default.
- W4310825102 hasOpenAccess W4310825102 @default.
- W4310825102 hasPrimaryLocation W43108251021 @default.
- W4310825102 hasRelatedWork W2554314924 @default.
- W4310825102 hasRelatedWork W2618858825 @default.
- W4310825102 hasRelatedWork W2953246223 @default.
- W4310825102 hasRelatedWork W2969399009 @default.
- W4310825102 hasRelatedWork W2998859928 @default.
- W4310825102 hasRelatedWork W3110074278 @default.
- W4310825102 hasRelatedWork W3151498616 @default.
- W4310825102 hasRelatedWork W4283584549 @default.
- W4310825102 hasRelatedWork W4293320219 @default.
- W4310825102 hasRelatedWork W4381885966 @default.
- W4310825102 isParatext "false" @default.
- W4310825102 isRetracted "false" @default.
- W4310825102 workType "article" @default.