Show simple item record

dc.contributor.authorChai, Lucy
dc.contributor.authorBau, David
dc.contributor.authorIsola, Phillip John
dc.date.accessioned2021-01-19T15:02:04Z
dc.date.available2021-01-19T15:02:04Z
dc.date.submitted2020-08
dc.identifier.issn0302-9743
dc.identifier.urihttps://hdl.handle.net/1721.1/129437
dc.description.abstractThe quality of image generation and manipulation is reaching impressive levels, making it increasingly difficult for a human to distinguish between what is real and what is fake. However, deep networks can still pick up on the subtle artifacts in these doctored images. We seek to understand what properties of fake images make them detectable and identify what generalizes across different model architectures, datasets, and variations in training. We use a patch-based classifier with limited receptive fields to visualize which regions of fake images are more easily detectable. We further show a technique to exaggerate these detectable properties and demonstrate that, even when the image generator is adversarially finetuned against a fake image classifier, it is still imperfect and leaves detectable artifacts in certain image patches. Code is available at https://github.com/chail/patch-forensics.en_US
dc.language.isoen
dc.publisherSpringer International Publishingen_US
dc.relation.isversionof10.1007/978-3-030-58574-7_7en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourcearXiven_US
dc.titleWhat Makes Fake Images Detectable? Understanding Properties that Generalizeen_US
dc.typeArticleen_US
dc.identifier.citationChai, Lucy et al. “What Makes Fake Images Detectable? Understanding Properties that Generalize.” ECCV 2020: 16th European Conference on Computer Vision, Lecture Notes in Computer Science, 12371. © 2020 The Author(s)en_US
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratoryen_US
dc.relation.journalLecture Notes in Computer Scienceen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2020-12-18T18:35:55Z
dspace.orderedauthorsChai, L; Bau, D; Lim, SN; Isola, Pen_US
dspace.date.submission2020-12-18T18:36:05Z
mit.journal.volume12371 LNCSen_US
mit.licenseOPEN_ACCESS_POLICY


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record