On Choosing the $μ$ Parameter in Gaussian Differential Privacy
Recent work argues for using Gaussian differential privacy (GDP) to report the privacy guarantees in privacy-preserving machine learning. We provide principled mappings from pure-DP $\varepsilon$ to GDP $μ$ by matching the worst-case success of a strong-adversary membership inference attack in terms of three metrics: multiplicative advantage at fixed FPR, precision at fixed recall, and the standard privacy profile. We tabulate $μ$ values across a useful range of parameters and recommend $μ\approx \varepsilon/5$ as a conservative general-purpose conversion.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Quantifying identifiability to choose and audit $ε$ in differentially private deep learning
Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists must choose privacy parameters $(\epsilon,\…
BIG-bench Machine LearningInference AttackInfinitely divisible privacy and beyond I: resolution of the $s^2=2k$ conjecture
Differential privacy is increasingly formalized through the lens of hypothesis testing via the robust and interpretable $f$-DP framework, where privacy guarantees are encoded by a baseline Blackwell trade-off function $f…
Fully Adaptive Composition for Gaussian Differential Privacy
We show that Gaussian Differential Privacy, a variant of differential privacy tailored to the analysis of Gaussian noise addition, composes gracefully even in the presence of a fully adaptive analyst. Such an analyst sel…
Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?
For small privacy parameter $\epsilon$, $\epsilon$-differential privacy (DP) provides a strong worst-case guarantee that no membership inference attack (MIA) can succeed at determining whether a person's data was used to…
Inference AttackMembership Inference AttackDifferentially private sub-Gaussian location estimators
We tackle the problem of estimating a location parameter with differential privacy guarantees and sub-Gaussian deviations. Recent work in statistics has focused on the study of estimators that achieve sub-Gaussian type d…