An auditor based on membership inference attacks computes valid lower bounds on the unlearning parameter ε, empirically separating certified unlearning methods (small bounds) from heuristic ones (large bounds).
Title resolution pending
2 Pith papers cite this work, alongside 399 external citations. Polarity classification is still indexing.
2
Pith papers citing it
399
external citations · OpenAlex
representative citing papers
Sufficient conditions using the Wasserstein metric of order 1 are derived to calibrate Laplace noise for pufferfish privacy in multi-user aggregated queries, with relaxations for binary data that reduce noise while preserving indistinguishability.
citing papers explorer
-
Auditing of Unlearning Algorithms
An auditor based on membership inference attacks computes valid lower bounds on the unlearning parameter ε, empirically separating certified unlearning methods (small bounds) from heuristic ones (large bounds).
-
Multi-user Pufferfish Privacy
Sufficient conditions using the Wasserstein metric of order 1 are derived to calibrate Laplace noise for pufferfish privacy in multi-user aggregated queries, with relaxations for binary data that reduce noise while preserving indistinguishability.