The paper proposes an over-unlearning metric and a prototype-based relearning attack for class-level machine unlearning, together with a defense objective called Spotter.
Specifically, for each forget sample x∈ Df , we draw a noise δ∼ N(0, σ2I) with variance σ2 = 0.01 to form perturbed sample x+δ
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.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack
The paper proposes an over-unlearning metric and a prototype-based relearning attack for class-level machine unlearning, together with a defense objective called Spotter.