RULI is a per-sample, dual-objective inference attack that measures privacy leakage and unlearning efficacy, showing average-case evaluations understate privacy risk.
Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell
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.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
RULI is a per-sample, dual-objective inference attack that measures privacy leakage and unlearning efficacy, showing average-case evaluations understate privacy risk.