Counting the iterations required to craft an adversarial example can reveal whether a sample was in the model's training set.
Scalable membership inference attacks via quantile regression
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
background 1representative citing papers
citing papers explorer
-
Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack
Counting the iterations required to craft an adversarial example can reveal whether a sample was in the model's training set.