CENTAUR speeds up privacy-preserving Transformer inference by permuting model weights and secret-sharing the input, at the cost of replacing provable privacy with empirical attack resistance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference
CENTAUR speeds up privacy-preserving Transformer inference by permuting model weights and secret-sharing the input, at the cost of replacing provable privacy with empirical attack resistance.