A conditional GAN adds transferable, self-erasable semantic masks that break black-box face recognition while allowing a trusted partner to reconstruct the original face.
Pixel privacy. increasing image appeal while blocking automatic inference of sensitive scene information,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
ErasableMask: A Robust and Erasable Privacy Protection Scheme against Black-box Face Recognition Models
A conditional GAN adds transferable, self-erasable semantic masks that break black-box face recognition while allowing a trusted partner to reconstruct the original face.