Caliber maps a target accuracy-retention level to a Gaussian logit-noise variance using a margin-normalized logistic curve, and derives the per-input query multiplier needed to average the noise away.
In: USENIX Se- curity (2018)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs
Caliber maps a target accuracy-retention level to a Gaussian logit-noise variance using a margin-normalized logistic curve, and derives the per-input query multiplier needed to average the noise away.