Per-sample gradient noise and exponential down-weighting of LIRA-identified vulnerable points reduce membership inference success on CIFAR-10 while keeping test accuracy near baseline.
Mem- bership inference attacks from first principles
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Technical Report for the Forgotten-by-Design Project: Targeted Obfuscation for Machine Learning
Per-sample gradient noise and exponential down-weighting of LIRA-identified vulnerable points reduce membership inference success on CIFAR-10 while keeping test accuracy near baseline.