Work Session on Statistical Data Confidentiality 2019

Comprehensive and other presentations

Organizers: Steering Committee

Session 1: Access to microdata

Session Organizers: Aleksandra Bujnowska (Eurostat), Janika Tarkoma (Statistics Finland) and Steven Thomas (Statistics Canada)

Session 1.1: Microdata access facilities

Romania NIS – Microdata for scientific purposes. Lucian Alexandrescu (National Institute of Statistics of Romania)

Presentation

Joint Safe Center at the Hungarian Academy of Sciences. Zoltán Vereczkei (Hungarian Central Statistical Office), János Köllő (Hungarian Academy of Sciences)

Virtual data labs - A more flexible approach to access Statistics Canada microdata. Kelly Cranswick (Statistics Canada)

Interoperability Challenges in Access to Microdata. Natalia Volkow (INEGI)

Data Confidentiality in ICBS Research Rooms. Julia Vider (CBS, Israel)

Accessing Data in the ONS Secure Research Service: A Certification Regime for Remote Connectivity. Andrew Engeli (ONS, UK)

Session 3: Risk assessment

Session Organizers: : Josep Domingo-Ferrer (Universitat Rovira i Virgili), Krish Muralidhar (University of Oklahoma)

Optimising the Trade-off between Information Utility and Disclosure Risk in a GA Synthetic Data Generator. Yingrui Chen, Jennifer Taub, Mark Elliot (University of Manchester)

10 is the safest number that there’s ever been. Felix Ritchie (University of the West of England)

The Synthetic Data Challenge. Mark Elliot and Jennifer Taub (University of Manchester)

Connecting privacy models and statistical disclosure control methods through bistochastic anonymization. Krish Muralidhar (U.Oklahoma), Nicolas Ruiz (OECD), Josep Domingo-Ferrer (URV)

Privacy, confidentiality, disclosure: What is the difference ? Krish Muralidhar (University of Oklahoma), Rathindra Sarathy (Oklahoma State University)

Session 6: Confidentiality issues of the Census 2020/2021 round

Session Organizers: Eric Schulte Nordholt (Statistics Netherlands)

A framework for assessing perturbative methods for protection of Census 2021 data at Statistics Portugal. Ines Rodrigues, Paula Campos and Teresa Fragoso (Statistics Portugal)

Paper

Session 2: Tabular data

Session Organizers: Sarah Giessing (Destatis)

Draft concepts for generalising tools implementing the cell key method to the case of continuous variables. Sarah Giessing and Reinhard Tent (Destatis)

Computational experience with stabilized Benders for the cell suppression problem. Daniel Baena, Jordi Castro and Antonio Frangioni (Universitat Politecnica de Catalunya)

Releasable inner cell frequencies by post-processing protected tabular data. Øyvind Langsrud (Statistics Norway)

Primary analysis of disclosure risk in tabular data from a Brazilian economic survey. Samela Batista Arantes and Maysa S. de Magalhaes (Brazilian Institute of Geography and Statistics)

Algorithmic Matching Attacks on Optimally Suppressed Tabular Data. Kazuhiro Minami (The Institute of Statistical Mathematics, Tokyo)

Session 1.2: Microdata protection

Session Organizer: Aleksandra Bujnowska (Eurostat), Janika Tarkoma (Statistics Finland) and Steven Thomas (Statistics Canada)

Promoting Statistical Disclosure Control for novices:  A Handbook. Richard Welpton (The Health Foundation), Arne Wolters (The Health Foundation), Emily Griffiths (University of Manchester), James Scott and Christine Woods (University of Essex)

Synthetic data generation for anonymization purposes. Application on the Norwegian Survey on living conditions/EHIS. Johan Heldal and Diana-Cristina Iancu (Statistics Norway)

A practice guide for microdata anonymization. Thijs Benschop and Matthew Welch (World Bank)

Training research output checkers. Felix Ritchie (University of the West of England)

Creation of synthetic microdata using dummy random variables of high dimension statistics based on big data. Institute of Economic Research, Hitotsubashi University

Session 5: Framework for confidentiality

Session Organizer: Aleksandra Bujnowska (Eurostat), Janika Tarkoma (Statistics Finland)

Understanding personalities in data access decision-making. Richard Welpton (The Health Foundation)

Successes and Challenges in Increasing Accessibility at Statistics Canada. Steven Thomas (Statistics Canada)

Evaluation criteria for the selection of the SDC Method. Christiane Seifert, Johannes Rohde (IT.NRW) and Sarah Giessing (Destatis)

Crisis management – training, practicing and testing. Janika Tarkoma and Harri Koskinen (Statistics Finland)

Statistical confidentiality in the range of measures safeguarding privacy of data subjects. Aleksandra Bujnowska (Eurostat)

Session 4: Emerging issues

Session Organizer: Josep Domingo-Ferrer (Universitat Rovira i Virgili)

Comparing methods of safely plotting variables on a map. Y. (Sapphire) Han, Peter-Paul de Wolf and Edwin de Jonge (Statistics Netherlands)

Private Set Intersection with Analytics. Guiseppe Bruno and Diana Nicoletti (Bank of Italy), Monica Scannapieco and Diego Zardetto (Istat)

The Potential of Anonymization Methods for Creating Detailed Geographical Data in Japan. Shinsuke Ito and Masayuki Terada (Chuo University)

Protecting consumer privacy in smart metering by randomized response. Josep Domingo-Ferrer, Bastian Stolb, David Sanchez (Universitat Rovira i Virgili)

Challenges and experiences in anonymizing and disseminating microdata from agricultural surveys in the context of the FAO AGRISurvey program. Thijs Benschop, Clara Aida Khalil (FAO)

Session 7: Software tools for statistical data confidentiality

Session Organizer: Peter-Paul de Wolf (Statistics Netherlands)

cellKey - consistent perturbation of statistical tables. Bernhard Meindl (Statistics Austria) and Tobias Enderle (Destatis)

Microdata.no - Instant Access to Microdata. Johan Heldal, Svein Johansen, Ørnulf Risnes (Statistics Norway)