Choosing blindly but wisely: differentially private solicitation of DNA datasets for disease marker discovery
نویسندگان
چکیده
منابع مشابه
Choosing blindly but wisely: differentially private solicitation of DNA datasets for disease marker discovery
OBJECTIVE To propose a new approach to privacy preserving data selection, which helps the data users access human genomic datasets efficiently without undermining patients' privacy. METHODS Our idea is to let each data owner publish a set of differentially-private pilot data, on which a data user can test-run arbitrary association-test algorithms, including those not known to the data owner a...
متن کاملChoosing Wisely
Purpose of review: The purpose of this review is to contribute to the Choosing Wisely Canada campaign and develop a list of 5 items for nephrology health care professionals and patients to re-evaluate based on evidence that they are overused or misused. Sources of information: A working group was formed from the Canadian Society of Nephrology (CSN) Clinical Practice Guidelines Committee. This w...
متن کاملGetting from choosing wisely to spending wisely.
It is intuitively true that the most just ways of reducing health care costs are to reduce unnecessary tests and interventions and improve the efficiency of care. Neither of these imperils outcomes (and may improve many) nor involves restricting care (and developing efficient care may require expansion of overall care). The first activity comes under the aegis of reducing waste, and the second,...
متن کاملGenerating Differentially Private Datasets Using GANs
In this paper, we present a technique for generating artificial datasets that retain statistical properties of the real data while providing differential privacy guarantees with respect to this data. We include a Gaussian noise layer in the discriminator of a generative adversarial network to make the output and the gradients differentially private with respect to the training data, and then us...
متن کاملGenerating Differentially Private Datasets Using Gans
In this paper, we present a technique for generating artificial datasets that retain statistical properties of the real data while providing differential privacy guarantees with respect to this data. We include a Gaussian noise layer in the discriminator of a generative adversarial network to make the output and the gradients differentially private with respect to the training data, and then us...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of the American Medical Informatics Association
سال: 2014
ISSN: 1527-974X,1067-5027
DOI: 10.1136/amiajnl-2014-003043