paper-with-me

홈 › Papers

Empirical Differential Privacy

2019-10-28 · Paul Burchard, Anthony Daoud, Dominic Dotterrer

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.

📄 PDF Abstract BibTeX arXiv:1910.12820

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM

2017-05-30 · Katrina Ligett, Seth Neel, Aaron Roth, Bo Waggoner 외

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

2017-12-01 · NeurIPS 2017 12 · Katrina Ligett, Seth Neel, Aaron Roth, Bo Waggoner 외

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

2019-12-24 · Daniel Bernau, Philip-William Grassal, Jonas Robl, Florian Kerschbaum

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 Attack

Evaluations of Machine Learning Privacy Defenses are Misleading

2024-04-26 · Michael Aerni, Jie Zhang, Florian Tramèr

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

2020-06-25 · Tatiana Komarova, Denis Nekipelov

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…