Deutsch
 
Benutzerhandbuch Datenschutzhinweis Impressum Kontakt
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Forschungspapier

Attributing Fake Images to GANs: Analyzing Fingerprints in Generated Images

MPG-Autoren
/persons/resource/persons225792

Yu,  Ning
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

Externe Ressourcen
Es sind keine Externen Ressourcen verfügbar
Volltexte (frei zugänglich)

arXiv:1811.08180.pdf
(Preprint), 3MB

Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Yu, N., Davis, L., & Fritz, M. (2018). Attributing Fake Images to GANs: Analyzing Fingerprints in Generated Images. Retrieved from http://arxiv.org/abs/1811.08180.


Zitierlink: http://hdl.handle.net/21.11116/0000-0002-95F8-E
Zusammenfassung
Research in computer graphics has been in pursuit of realistic image generation for a long time. Recent advances in machine learning with deep generative models have shown increasing success of closing the realism gap by using data-driven and learned components. There is an increasing concern that real and fake images will become more and more difficult to tell apart. We take a first step towards this larger research challenge by asking the question if and to what extend a generated fake image can be attribute to a particular Generative Adversarial Networks (GANs) of a certain architecture and trained with particular data and random seed. Our analysis shows single samples from GANs carry highly characteristic fingerprints which make attribution of images to GANs possible. Surprisingly, this is even possible for GANs with same architecture and same training that only differ by the training seed.