A single family of DP bounds covers membership inference, attribute inference, and reconstruction for multiple targets, non-uniform priors, and approximate success metrics, depending only on epsilon and the attacker's prior success rate.
Learning with privacy at scale
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.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Unified Framework for Adversary-Aware Differential Privacy Bounds
A single family of DP bounds covers membership inference, attribute inference, and reconstruction for multiple targets, non-uniform priors, and approximate success metrics, depending only on epsilon and the attacker's prior success rate.