An Ad Omnia Approach to Defining and Achieving Private Data Analysis

By Cynthia Dwork. 2007

78 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Sociology and Political Science

Citations in the corpus

Boosting and Differential Privacy (2010, background): “See [7], [6] for more properties and results concerning differential”
Efficient, Differentially Private Point Estimators (2008, methodology): “These are surveyed by Dwork [ 13 , 14] and Nissim [28].”
Protecting privacy when mining and sharing user data (2012, background): “We have built a case, supported also by decades of research in cryptography [44], that ad-hoc approaches to protecting privacy inevitably fail in the world of creative and sophisticated adversaries in possession of auxiliary information from multiple sources.”
Differentially Private SQL with Bounded User Contribution (2019, background): “The standard definition used in this context is differential privacy (DP): it provides a formal guarantee on how much the output of an algorithm reveals about any individual in its input [10, 11, 14].”
Airavat: Security and Privacy for MapReduce (2010, background): “formation will never be available to the adversary [15, 16].”
Differential privacy and robust statistics (2009, background): “Differential privacy is also an ad omnia (rather than ad hoc) guarantee, and addresses any concerns that an individual might have about allowing her data to be included in a database (see [6] for further discussion of this point).”
Privacy-Preserving Distributed Multi-Task Learning with Asynchronous Updates (2017, background): “…privacy makes sure that the adversary’s prior and posterior views about an individual (i.e. before and after having access to the database) shouldn’t be “drastically different” or the access to the database shouldn’t change the adversary’s views about any individual “too much” [17, 30].”
Differential privacy under continual observation (2010, background): “Categories and Subject Descriptors F.2.0 [Theory of Computation]: Analysis of Algorithms and problem complexity General * Research supported by a grant from the Israel Science Foundation.”
The application of differential privacy to health data (2012, background): “Dwork mentions in [13] that “conversations with experts in this field involve pleas for a noisy table that will permit highly accurate answers to be derived for computations that are not specified at the outset”.”
Differential privacy in new settings (2010, background): “Di.erential Privacy in New Settings Cynthia Dwork* Abstract Di.erential privacy is a recent notion of privacy tailored to the problem of statistical disclosure control: how to release statistical information about a set of people without compromising the the privacy of any individual [7].”