Empirical Differential Privacy
We show how to achieve differential privacy with no or reduced added noise, based on the empirical noise in the data itself. Unlike previous works on noiseless privacy, the empirical viewpoint avoids making any explicit assumptions about the random process generating the data.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM
Traditional approaches to differential privacy assume a fixed privacy requirement $\epsilon$ for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint. As differential p…
Accuracy First: Selecting a Differential Privacy Level for Accuracy Constrained ERM
Traditional approaches to differential privacy assume a fixed privacy requirement ε for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint. As differential privacy is…
Assessing differentially private deep learning with Membership Inference
Attacks that aim to identify the training data of public neural networks represent a severe threat to the privacy of individuals participating in the training data set. A possible protection is offered by anonymization o…
Deep LearningInference AttackMembership Inference AttackEvaluations of Machine Learning Privacy Defenses are Misleading
Empirical defenses for machine learning privacy forgo the provable guarantees of differential privacy in the hope of achieving higher utility while resisting realistic adversaries. We identify severe pitfalls in existing…
Identification and Formal Privacy Guarantees
Empirical economic research crucially relies on highly sensitive individual datasets. At the same time, increasing availability of public individual-level data makes it possible for adversaries to potentially de-identify…