Differential identifiability

By Jaewoo Lee, Chris Clifton. 2012

108 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Sociology and Political Science

Citations in the corpus

Privacy in Pharmacogenetics: An End-to-End Case Study of Personalized Warfarin Dosing (2014, neutral): “Lee and Clifton [30] recognize the problem of setting ε and its relationship to the relative nature of differential privacy, and later [31] propose an alternative parametization of differential privacy in terms of the probabil-”
Preserving differential privacy in convolutional deep belief networks (2017, background): “In [40], the authors proposed differential identifiability to link individual identifiability to differential privacy.”
Discrimination- and privacy-aware patterns (2015, background): “…under the name of privacy-aware data analysis, that focus on the privacy of the individuals whose data is collected in the database (Friedman et al. 2008; Atzori et al. 2008; Bhaskar et al. 2010; Friedman and Schuster 2010; Li et al. 2012; Lee and Clifton 2012; Zeng et al. 2012; Bonomi 2013).”
Differential Privacy Techniques for Cyber Physical Systems: A Survey (2018, background): “and differential identifiability [29] to address certain problems in differential privacy framework.”
On the relation between identifiability, differential privacy, and mutual-information privacy (2014, unknown): “…y) subject to pX|Y (x | y) ≤ e ipX|Y (x′ | y), ∀x, x′ ∈ Dn : x ∼ x′, y ∈ Dn, (8)∑ x∈Dn pX|Y (x | y) = 1, ∀y ∈ Dn, (9) pX|Y (x | y) ≥ 0, ∀x, y ∈ Dn, (10)∑ y∈Dn pX|Y (x | y)pY (y) = pX(x), ∀x ∈ Dn, (11) pY (y) ≥ 0, ∀y ∈ Dn. (12) The Privacy–Distortion Problem under Differential Privacy…”
On the Relation Between Identifiability, Differential Privacy, and Mutual-Information Privacy (2016, background): “Differential identifiability [17] and membership privacy [18] assume that a database entry can be traced back to the identify of an individual, and they quantify the leakage of the information on whether an individual participates the database or not.”
A Semi-Supervised Learning Approach to Differential Privacy (2013, background): “Lee and Clifton [16] gave a new formulation called differential identifiability.”
Regression Model Fitting under Differential Privacy and Model Inversion Attack (2015, background): “Another notable work [Lee and Clifton, 2012] studied the relationship of (cid:15) to the relative nature of differential privacy.”
Membership privacy: a unifying framework for privacy definitions (2013, unknown): “We begin by analyzing the recent privacy incidents.”
Towards Measuring Membership Privacy (2017, background): “Follow-up works on DP try to relax the background knowledge by building more realistic background knowledge models [6, 21, 23, 27, 41].”