John M. Abowd (former NCRN-Cornell PI) and other NCRN PIs present:
An Integrated Approach to Providing Access to Confidential Social Science Data — Jerome Reiter, Duke University
The Challenge of Reproducible Science and Privacy Protection for Statistical Agencies — John M. Abowd, U.S. Census Bureau/Cornell University
Spatio-Temporal Change of Support with Application to American Community Survey Multi-Year Period Estimates — Scott H. Holan, University of Missouri ; Jonathan R. Bradley, University of Missouri ; Christopher Wikle, University of Missouri
Lars Vilhuber chairs a session organized by the Committee on Privacy and Confidentiality and Aleksandra Slavkovic, Penn State University:
Connections Between Privacy Definitions and Arbitrage-Free Pricing Functions — Daniel Kifer, Penn State University
Differentially Private Statistical Inference and Hypothesis Testing — Vishesh Karwa, Carnegie Mellon University
Learning with Differential Privacy: Stability, Learnability, and the Sufficiency and Necessity of ERM Principle — Yu-Xiang Wang, Carnegie Mellon University ; Jing Lei, Carnegie Mellon University ; Stephen E. Fienberg, Carnegie Mellon University
Performance Bounds for Graphical Record Linkage: Can record linkage bounds provide guidance for private synthetic data release? — Rebecca Steorts, Duke University ; Matt Barnes, Carnegie Mellon University ; Willie Neisweigner, Carnegie Mellon University
Discussant: Adam Smith, Penn State University
Lars Vilhuber speaks about “Disclosure Limitation and Confidentiality Protection in Linked Data” at the Center for Interuniversity Research and Analysis of Organizations‘s conference on “Facilitate the access to Quebec data: How and to what ends?” The conference is jointly organized with the Quebec inter-University Centre for Social Statistics (QICSS). The presentation relies on joint work with John M. Abowd and Ian M. Schmutte.
“Confidentiality Protection and Physical Safeguards: A Review”
Lars Vilhuber, PhD
Confidentiality protection is a multi-layered concept, involving statistical (cryptographic) methods and physical safeguards. When providing access to researchers (both internal to the agency and external academic), a tension arises between the level of trust vis-à-vis the researcher, the statistical disclosure limitation applied to the data visible to the researcher; and the physical access mechanisms used by the researcher. This presentation will review systems used by national and private research organizations around the world, putting them into the relevant legal and societal context.