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).
The retain samples and sampled forget samples are then pooled and shuffled to form the training dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
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).