A stochastic, high-frequency-preserving anonymization method is claimed to keep faces unrecognizable to people while retaining 94.21% average accuracy on face recognition models that were not used during optimization.
Secure face matching using fully homomorphic encryption
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
background 1representative citing papers
citing papers explorer
-
Local Features Meet Stochastic Anonymization: Revolutionizing Privacy-Preserving Face Recognition for Black-Box Models
A stochastic, high-frequency-preserving anonymization method is claimed to keep faces unrecognizable to people while retaining 94.21% average accuracy on face recognition models that were not used during optimization.