New Lower Bounds for Differential Privacy: How Low Can You Go?
نویسندگان
چکیده
Mirror mirror on the wall, who’s tracing scheme is the fairest of them all. *Columbia University Department of Computer Science. [email protected]. †Columbia University Department of Computer Science. [email protected]. ‡Northeastern University College of Computer and Information Science. [email protected]. §Northeastern University College of Computer and Information Science. [email protected]
منابع مشابه
New Separations in the Complexity of Differential Privacy
In this thesis, we study when algorithmic tasks can be performed on sensitive data while protecting the privacy of individuals whose information is collected. We focus on the notion of differential privacy, which gives a strong formal guarantee that no individual’s data has a significant impact on the outcome of a computation. Intense study over the last decade has shown that a rich variety of ...
متن کاملConcentration Bounds for High Sensitivity Functions Through Differential Privacy
A new line of work [6, 9, 15, 2] demonstrates how differential privacy [8] can be used as a mathematical tool for guaranteeing generalization in adaptive data analysis. Specifically, if a differentially private analysis is applied on a sample S of i.i.d. examples to select a lowsensitivity function f , then w.h.p. f (S) is close to its expectation, although f is being chosen based on the data. ...
متن کاملRatio Buckets: A Numeric Method for r-Fold Tight Differential Privacy
Privacy guarantees of a privacy-enhancing system have to be robust against thousands of observations for many realistic application scenarios, such as anonymous communication systems, privacy-enhancing database queries, or privacy-enhancing machine-learning methods. The notion of r-fold Approximate Differential Privacy (ADP) offers a framework with clear privacy bounds and with composition theo...
متن کاملDifferential Privacy for Bayesian Inference through Posterior Sampling
Differential privacy formalises privacy-preserving mechanisms that provide access to a database. Can Bayesian inference be used directly to provide private access to data? The answer is yes: under certain conditions on the prior, sampling from the posterior distribution can lead to a desired level of privacy and utility. For a uniform treatment, we define differential privacy over arbitrary dat...
متن کاملLower Bounds in Differential Privacy
This paper is about private data analysis, in which a trusted curator holding a confidential database responds to real vector-valued queries. A common approach to ensuring privacy for the database elements is to add appropriately generated random noise to the answers, releasing only these noisy responses. A line of study initiated in [7] examines the amount of distortion needed to prevent priva...
متن کامل