Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036644531> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3036644531 abstract "An image forgery method called Deepfakes can cause security and privacy issues by changing the identity of a person in a photo through the replacement of his/her face with a computer-generated image or another person's face. Therefore, a new challenge of detecting Deepfakes arises to protect individuals from potential misuses. Many researchers have proposed various binary-classification based detection approaches to detect deepfakes. However, binary-classification based methods generally require a large amount of both real and fake face images for training, and it is challenging to collect sufficient fake images data in advance. Besides, when new deepfakes generation methods are introduced, little deepfakes data will be available, and the detection performance may be mediocre. To overcome these data scarcity limitations, we formulate deepfakes detection as a one-class anomaly detection problem. We propose OC-FakeDect, which uses a one-class Variational Autoencoder (VAE) to train only on real face images and detects non-real images such as deepfakes by treating them as anomalies. Our preliminary result shows that our one class-based approach can be promising when detecting Deepfakes, achieving a 97.5% accuracy on the NeuralTextures data of the well-known FaceForensics++ benchmark dataset without using any fake images for the training process." @default.
- W3036644531 created "2020-06-25" @default.
- W3036644531 creator A5033106393 @default.
- W3036644531 creator A5046825295 @default.
- W3036644531 date "2020-06-01" @default.
- W3036644531 modified "2023-10-09" @default.
- W3036644531 title "OC-FakeDect: Classifying Deepfakes Using One-class Variational Autoencoder" @default.
- W3036644531 cites W1834627138 @default.
- W3036644531 cites W2132870739 @default.
- W3036644531 cites W2155319953 @default.
- W3036644531 cites W2281375574 @default.
- W3036644531 cites W2486034530 @default.
- W3036644531 cites W2531409750 @default.
- W3036644531 cites W2726515241 @default.
- W3036644531 cites W2738406145 @default.
- W3036644531 cites W2901773810 @default.
- W3036644531 cites W2902962850 @default.
- W3036644531 cites W2914447220 @default.
- W3036644531 cites W2942074357 @default.
- W3036644531 cites W2962770929 @default.
- W3036644531 cites W2962858109 @default.
- W3036644531 cites W2962896155 @default.
- W3036644531 cites W2962958939 @default.
- W3036644531 cites W2970868842 @default.
- W3036644531 cites W2982058372 @default.
- W3036644531 cites W2997520009 @default.
- W3036644531 cites W3101998545 @default.
- W3036644531 cites W3106257921 @default.
- W3036644531 doi "https://doi.org/10.1109/cvprw50498.2020.00336" @default.
- W3036644531 hasPublicationYear "2020" @default.
- W3036644531 type Work @default.
- W3036644531 sameAs 3036644531 @default.
- W3036644531 citedByCount "76" @default.
- W3036644531 countsByYear W30366445312020 @default.
- W3036644531 countsByYear W30366445312021 @default.
- W3036644531 countsByYear W30366445312022 @default.
- W3036644531 countsByYear W30366445312023 @default.
- W3036644531 crossrefType "proceedings-article" @default.
- W3036644531 hasAuthorship W3036644531A5033106393 @default.
- W3036644531 hasAuthorship W3036644531A5046825295 @default.
- W3036644531 hasConcept C101738243 @default.
- W3036644531 hasConcept C108583219 @default.
- W3036644531 hasConcept C115961682 @default.
- W3036644531 hasConcept C119857082 @default.
- W3036644531 hasConcept C13280743 @default.
- W3036644531 hasConcept C144024400 @default.
- W3036644531 hasConcept C153180895 @default.
- W3036644531 hasConcept C154945302 @default.
- W3036644531 hasConcept C185798385 @default.
- W3036644531 hasConcept C205649164 @default.
- W3036644531 hasConcept C2777212361 @default.
- W3036644531 hasConcept C2779304628 @default.
- W3036644531 hasConcept C36289849 @default.
- W3036644531 hasConcept C41008148 @default.
- W3036644531 hasConcept C739882 @default.
- W3036644531 hasConceptScore W3036644531C101738243 @default.
- W3036644531 hasConceptScore W3036644531C108583219 @default.
- W3036644531 hasConceptScore W3036644531C115961682 @default.
- W3036644531 hasConceptScore W3036644531C119857082 @default.
- W3036644531 hasConceptScore W3036644531C13280743 @default.
- W3036644531 hasConceptScore W3036644531C144024400 @default.
- W3036644531 hasConceptScore W3036644531C153180895 @default.
- W3036644531 hasConceptScore W3036644531C154945302 @default.
- W3036644531 hasConceptScore W3036644531C185798385 @default.
- W3036644531 hasConceptScore W3036644531C205649164 @default.
- W3036644531 hasConceptScore W3036644531C2777212361 @default.
- W3036644531 hasConceptScore W3036644531C2779304628 @default.
- W3036644531 hasConceptScore W3036644531C36289849 @default.
- W3036644531 hasConceptScore W3036644531C41008148 @default.
- W3036644531 hasConceptScore W3036644531C739882 @default.
- W3036644531 hasLocation W30366445311 @default.
- W3036644531 hasOpenAccess W3036644531 @default.
- W3036644531 hasPrimaryLocation W30366445311 @default.
- W3036644531 hasRelatedWork W2292254049 @default.
- W3036644531 hasRelatedWork W2592385986 @default.
- W3036644531 hasRelatedWork W2897995864 @default.
- W3036644531 hasRelatedWork W2998168123 @default.
- W3036644531 hasRelatedWork W3105816646 @default.
- W3036644531 hasRelatedWork W4226497253 @default.
- W3036644531 hasRelatedWork W4281924768 @default.
- W3036644531 hasRelatedWork W4287995534 @default.
- W3036644531 hasRelatedWork W4310034804 @default.
- W3036644531 hasRelatedWork W4376852344 @default.
- W3036644531 isParatext "false" @default.
- W3036644531 isRetracted "false" @default.
- W3036644531 magId "3036644531" @default.
- W3036644531 workType "article" @default.