Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225972486> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4225972486 abstract "With the rapid progress of generation technology, it has become necessary to attribute the origin of fake images. Existing works on fake image attribution perform multi-class classification on several Generative Adversarial Network (GAN) models and obtain high accuracies. While encouraging, these works are restricted to model-level attribution, only capable of handling images generated by seen models with a specific seed, loss and dataset, which is limited in real-world scenarios when fake images may be generated by privately trained models. This motivates us to ask whether it is possible to attribute fake images to the source models' architectures even if they are finetuned or retrained under different configurations. In this work, we present the first study on Deepfake Network Architecture Attribution to attribute fake images on architecture-level. Based on an observation that GAN architecture is likely to leave globally consistent fingerprints while traces left by model weights vary in different regions, we provide a simple yet effective solution named DNA-Det for this problem. Extensive experiments on multiple cross-test setups and a large-scale dataset demonstrate the effectiveness of DNA-Det." @default.
- W4225972486 created "2022-05-05" @default.
- W4225972486 creator A5006558049 @default.
- W4225972486 creator A5056924576 @default.
- W4225972486 creator A5060270456 @default.
- W4225972486 creator A5062934821 @default.
- W4225972486 creator A5075889094 @default.
- W4225972486 date "2022-02-28" @default.
- W4225972486 modified "2023-10-16" @default.
- W4225972486 title "Deepfake Network Architecture Attribution" @default.
- W4225972486 doi "https://doi.org/10.48550/arxiv.2202.13843" @default.
- W4225972486 hasPublicationYear "2022" @default.
- W4225972486 type Work @default.
- W4225972486 citedByCount "0" @default.
- W4225972486 crossrefType "posted-content" @default.
- W4225972486 hasAuthorship W4225972486A5006558049 @default.
- W4225972486 hasAuthorship W4225972486A5056924576 @default.
- W4225972486 hasAuthorship W4225972486A5060270456 @default.
- W4225972486 hasAuthorship W4225972486A5062934821 @default.
- W4225972486 hasAuthorship W4225972486A5075889094 @default.
- W4225972486 hasBestOaLocation W42259724861 @default.
- W4225972486 hasConcept C108583219 @default.
- W4225972486 hasConcept C111472728 @default.
- W4225972486 hasConcept C119857082 @default.
- W4225972486 hasConcept C121332964 @default.
- W4225972486 hasConcept C123657996 @default.
- W4225972486 hasConcept C124101348 @default.
- W4225972486 hasConcept C138885662 @default.
- W4225972486 hasConcept C142362112 @default.
- W4225972486 hasConcept C143299363 @default.
- W4225972486 hasConcept C153349607 @default.
- W4225972486 hasConcept C154945302 @default.
- W4225972486 hasConcept C15744967 @default.
- W4225972486 hasConcept C193415008 @default.
- W4225972486 hasConcept C2777212361 @default.
- W4225972486 hasConcept C2778755073 @default.
- W4225972486 hasConcept C2780586882 @default.
- W4225972486 hasConcept C2988773926 @default.
- W4225972486 hasConcept C37736160 @default.
- W4225972486 hasConcept C38652104 @default.
- W4225972486 hasConcept C39890363 @default.
- W4225972486 hasConcept C41008148 @default.
- W4225972486 hasConcept C62520636 @default.
- W4225972486 hasConcept C77805123 @default.
- W4225972486 hasConceptScore W4225972486C108583219 @default.
- W4225972486 hasConceptScore W4225972486C111472728 @default.
- W4225972486 hasConceptScore W4225972486C119857082 @default.
- W4225972486 hasConceptScore W4225972486C121332964 @default.
- W4225972486 hasConceptScore W4225972486C123657996 @default.
- W4225972486 hasConceptScore W4225972486C124101348 @default.
- W4225972486 hasConceptScore W4225972486C138885662 @default.
- W4225972486 hasConceptScore W4225972486C142362112 @default.
- W4225972486 hasConceptScore W4225972486C143299363 @default.
- W4225972486 hasConceptScore W4225972486C153349607 @default.
- W4225972486 hasConceptScore W4225972486C154945302 @default.
- W4225972486 hasConceptScore W4225972486C15744967 @default.
- W4225972486 hasConceptScore W4225972486C193415008 @default.
- W4225972486 hasConceptScore W4225972486C2777212361 @default.
- W4225972486 hasConceptScore W4225972486C2778755073 @default.
- W4225972486 hasConceptScore W4225972486C2780586882 @default.
- W4225972486 hasConceptScore W4225972486C2988773926 @default.
- W4225972486 hasConceptScore W4225972486C37736160 @default.
- W4225972486 hasConceptScore W4225972486C38652104 @default.
- W4225972486 hasConceptScore W4225972486C39890363 @default.
- W4225972486 hasConceptScore W4225972486C41008148 @default.
- W4225972486 hasConceptScore W4225972486C62520636 @default.
- W4225972486 hasConceptScore W4225972486C77805123 @default.
- W4225972486 hasLocation W42259724861 @default.
- W4225972486 hasOpenAccess W4225972486 @default.
- W4225972486 hasPrimaryLocation W42259724861 @default.
- W4225972486 hasRelatedWork W2729909199 @default.
- W4225972486 hasRelatedWork W2753252132 @default.
- W4225972486 hasRelatedWork W2765644156 @default.
- W4225972486 hasRelatedWork W2904022596 @default.
- W4225972486 hasRelatedWork W3000617323 @default.
- W4225972486 hasRelatedWork W3007138654 @default.
- W4225972486 hasRelatedWork W3087084548 @default.
- W4225972486 hasRelatedWork W3102190267 @default.
- W4225972486 hasRelatedWork W3156291593 @default.
- W4225972486 hasRelatedWork W3201064385 @default.
- W4225972486 isParatext "false" @default.
- W4225972486 isRetracted "false" @default.
- W4225972486 workType "article" @default.