Approximate unlearning leaves loss-landscape residuals that a fine-tuning-based attack can exploit for membership inference, and the proposed OUR method scrubs these residuals.
Rmr: A relative membership risk measure for machine learning mod- els
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
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy
Approximate unlearning leaves loss-landscape residuals that a fine-tuning-based attack can exploit for membership inference, and the proposed OUR method scrubs these residuals.