Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205653724> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W3205653724 abstract "Deepfake videos are videos where the features of a person are replaced with the features of another person. Videos can be manipulated using powerful Deep Learning techniques. This technology may be used maliciously as a means of misinformation, manipulation, and persuasion. There are currently not many solutions to identify products of Deepfake technology, although there is significant research being conducted to tackle this problem. One often researched deep learning technology is the Generative Adversarial Network (GAN). These networks are commonly used to generate Deepfake videos but not used for their detection. In this work, we explore solutions based on GAN discriminators as a means to detect Deepfake videos. Using MesoNet as a baseline, we train a GAN and extract the discriminator as a dedicated module to detect Deepfakes. We test several discriminator architectures using multiple datasets to explore how the efficacy of the discriminator varies with different setups and training methods. Finally, we propose a model to boost the efficacy of a group of GAN discriminators using ensemble methods. Our results show that GAN discriminators, even augmented by ensemble methods, do not perform well on videos from unknown sources." @default.
- W3205653724 created "2021-10-25" @default.
- W3205653724 creator A5011615128 @default.
- W3205653724 creator A5014486622 @default.
- W3205653724 creator A5026020993 @default.
- W3205653724 creator A5067872700 @default.
- W3205653724 creator A5083435293 @default.
- W3205653724 date "2021-08-01" @default.
- W3205653724 modified "2023-09-26" @default.
- W3205653724 title "Deepfake Detection using GAN Discriminators" @default.
- W3205653724 cites W2133665775 @default.
- W3205653724 cites W2891145043 @default.
- W3205653724 cites W2920877282 @default.
- W3205653724 cites W3012455256 @default.
- W3205653724 doi "https://doi.org/10.1109/bigdataservice52369.2021.00014" @default.
- W3205653724 hasPublicationYear "2021" @default.
- W3205653724 type Work @default.
- W3205653724 sameAs 3205653724 @default.
- W3205653724 citedByCount "2" @default.
- W3205653724 countsByYear W32056537242022 @default.
- W3205653724 countsByYear W32056537242023 @default.
- W3205653724 crossrefType "proceedings-article" @default.
- W3205653724 hasAuthorship W3205653724A5011615128 @default.
- W3205653724 hasAuthorship W3205653724A5014486622 @default.
- W3205653724 hasAuthorship W3205653724A5026020993 @default.
- W3205653724 hasAuthorship W3205653724A5067872700 @default.
- W3205653724 hasAuthorship W3205653724A5083435293 @default.
- W3205653724 hasConcept C108583219 @default.
- W3205653724 hasConcept C119857082 @default.
- W3205653724 hasConcept C154945302 @default.
- W3205653724 hasConcept C2776990098 @default.
- W3205653724 hasConcept C2779803651 @default.
- W3205653724 hasConcept C2988773926 @default.
- W3205653724 hasConcept C38652104 @default.
- W3205653724 hasConcept C39890363 @default.
- W3205653724 hasConcept C41008148 @default.
- W3205653724 hasConcept C76155785 @default.
- W3205653724 hasConcept C94915269 @default.
- W3205653724 hasConceptScore W3205653724C108583219 @default.
- W3205653724 hasConceptScore W3205653724C119857082 @default.
- W3205653724 hasConceptScore W3205653724C154945302 @default.
- W3205653724 hasConceptScore W3205653724C2776990098 @default.
- W3205653724 hasConceptScore W3205653724C2779803651 @default.
- W3205653724 hasConceptScore W3205653724C2988773926 @default.
- W3205653724 hasConceptScore W3205653724C38652104 @default.
- W3205653724 hasConceptScore W3205653724C39890363 @default.
- W3205653724 hasConceptScore W3205653724C41008148 @default.
- W3205653724 hasConceptScore W3205653724C76155785 @default.
- W3205653724 hasConceptScore W3205653724C94915269 @default.
- W3205653724 hasLocation W32056537241 @default.
- W3205653724 hasOpenAccess W3205653724 @default.
- W3205653724 hasPrimaryLocation W32056537241 @default.
- W3205653724 hasRelatedWork W2904022596 @default.
- W3205653724 hasRelatedWork W2952541330 @default.
- W3205653724 hasRelatedWork W2975432854 @default.
- W3205653724 hasRelatedWork W3105974085 @default.
- W3205653724 hasRelatedWork W3192801748 @default.
- W3205653724 hasRelatedWork W3197610371 @default.
- W3205653724 hasRelatedWork W3198359486 @default.
- W3205653724 hasRelatedWork W3201064385 @default.
- W3205653724 hasRelatedWork W4280544492 @default.
- W3205653724 hasRelatedWork W4301431435 @default.
- W3205653724 isParatext "false" @default.
- W3205653724 isRetracted "false" @default.
- W3205653724 magId "3205653724" @default.
- W3205653724 workType "article" @default.