The paper establishes finite-sample lower bounds on the true MMSE of sensitive feature inference, expressed as empirical MSE minus finite-sample and approximation error terms, with closed-form approximation bounds for linear models.
Auditing privacy of additive noise mechanisms using linear predictive models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Lower Bounds on the MMSE of Adversarially Inferring Sensitive Features
The paper establishes finite-sample lower bounds on the true MMSE of sensitive feature inference, expressed as empirical MSE minus finite-sample and approximation error terms, with closed-form approximation bounds for linear models.