An unlearned model can be used as a noisy teacher to reconstruct the class labels of data that machine unlearning was supposed to forget, without access to the original model.
Model inversion attacks that exploit confidence information and basic countermeasures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy
An unlearned model can be used as a noisy teacher to reconstruct the class labels of data that machine unlearning was supposed to forget, without access to the original model.