Newer 'relaxed' differential privacy analyses yield tighter upper-bound guarantees without changing actual privacy loss, and attack success can be translated into a lower bound on that loss.
Learning with pri- vacy at scale
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
That which we call private
Newer 'relaxed' differential privacy analyses yield tighter upper-bound guarantees without changing actual privacy loss, and attack success can be translated into a lower bound on that loss.