Combining Matryoshka-style compression, CKKS fully homomorphic encryption, and an encrypted-domain PolyProtect hash reduces age, gender, and ethnicity inference from face embeddings to near-random levels while preserving identification accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Shielding Latent Face Representations From Privacy Attacks
Combining Matryoshka-style compression, CKKS fully homomorphic encryption, and an encrypted-domain PolyProtect hash reduces age, gender, and ethnicity inference from face embeddings to near-random levels while preserving identification accuracy.