Worst-Case Morphs: a Theoretical and a Practical Approach

Zusammenfassung
Face Recognition (FR) systems have been shown to be vulnerable to morphing attacks. We examine exactly how challenging morphs can become. By showing a worst-case construction in the embedding space of an FR system and using a mapping from embedding space back to image space we generate images that show that this theoretical upper bound can be approximated if the FR system is known. The resulting morphs can also succesfully fool unseen FR systems and are useful for exploring and understanding the weaknesses of FR systems. Our method contributes to gaining more insight into the vulnerability of FR systems.
  • Vollständige Referenz
  • BibTeX
Una Kelly, L. S., (2022). Worst-Case Morphs: a Theoretical and a Practical Approach. In: Brömme, A., Damer, N., Gomez-Barrero, M., Raja, K., Rathgeb, C., , ., Todisco, M. & Uhl, A. (Hrsg.), BIOSIG 2022. Bonn: Gesellschaft für Informatik e.V.. (S. 63-71). DOI: 10.1109/BIOSIG55365.2022.9896965
@inproceedings{mci/Una Kelly2022,
author = {Una Kelly, Luuk Spreeuwers and Raymond Veldhuis},
title = {Worst-Case Morphs: a Theoretical and a Practical Approach},
booktitle = {BIOSIG 2022},
year = {2022},
editor = {Brömme, Arslan AND Damer, Naser AND Gomez-Barrero, Marta AND Raja, Kiran AND Rathgeb, Christian AND Sequeira Ana F. AND Todisco, Massimiliano AND Uhl, Andreas} ,
pages = { 63-71 } ,
doi = { 10.1109/BIOSIG55365.2022.9896965 },
publisher = {Gesellschaft für Informatik e.V.},
address = {Bonn}
}
DateienGroesseFormatAnzeige
06-BIOSIG_2022_paper_24.pdf397.9Kb PDF Öffnen

Sollte hier kein Volltext (PDF) verlinkt sein, dann kann es sein, dass dieser aus verschiedenen Gruenden (z.B. Lizenzen oder Copyright) nur in einer anderen Digital Library verfuegbar ist. Versuchen Sie in diesem Fall einen Zugriff ueber die verlinkte DOI: 10.1109/BIOSIG55365.2022.9896965

Haben Sie fehlerhafte Angaben entdeckt? Sagen Sie uns Bescheid: Feedback abschicken