PROGRAMME
WEDNESDAY, 17 SEPTEMBER
- 8:30 - Registration
- 9:30 - Opening Session
Synthetic Data I
Session Chair: Jörg Drechsler
- 9:45 - Disclosure Risk Evaluation for Fully Synthetic Categorical Data. Jingchen Hu, Jerome Reiter and Quanli Wang
- 10:10 - v-Dispersed Synthetic Data Based on a Mixture Model with Constraints. Anna Oganian
- 10:35 - Nonparametric Generation of Synthetic Data for Small Geographic Areas. Joseph W. Sakshaug and Trivellore E. Raghunathan
- 11:00 - Using Partially Synthetic Data to Replace Suppression in the Business Dynamics Statistics: Early Results. Javier Miranda and Lars Vilhuber
11:25 - Coffee Break
Synthetic Data II
Session Chair: Jordi Castro
- 11:50 - Synthetic Longitudinal Business Databases for International Comparisons. Jörg Drechsler and Lars Vilhuber
- 12:15 - Simple methods for providing synthetic data for the UK longitudinal studies. Gillian M. Raab, Beata Nowok and Chris Dibben (*)
- 12:30 - Methods and Tools for the Generation of Synthetic Populations. A Brief Review. Matthias Templ and Bernhard Meindl (*)
12:45 - Lunch
Microdata Masking
Session Chair: Aleksandra Slavkovic
- 14:40 - Density Approximant Based on Noise Multiplied Data. Yan-Xia Lin
- 15:05 - Reverse Mapping to Preserve the Marginal Distributions of Attributes in Masked Microdata. Krishnamurty Muralidhar, Rathindra Sarathy and Josep Domingo-Ferrer
- 15:30 - JPEG-based Microdata Protection. Javier Jiménez, Guillermo Navarro-Arribas and Vicenç Torra
- 15:45 - Ontology-Based Quality Evaluation of Value Generalization Hierarchies for Data Anonymization. Vanessa Ayala-Rivera, Patrick McDonagh, Thomas Cerqueus and Liam Murphy (*)
- 16:00 - Data Swapping as a More Efficient Tool to Create Anonymized Census Microdata in Japan. Shinsuke Ito (*)
16:15 - Coffee Break
Record Linkage
Session Chair: Vicenç Torra
- 16:35 - A Comparison of Blocking Methods for Record Linkage. Rebecca C. Steorts, Samuel L. Ventura, Mauricio Sadinle and Stephen E. Fienberg
- 17:00 - Probabilistic Record Linkage for Disclosure Risk Assessment. Natalie Shlomo
- 17:25 - Hierarchical Linkage Clustering with Distributions of Distances for Large-Scale Record Linkage. Samuel L. Ventura, Rebecca Nugent and Erica R.H. Fuchs
- 17:50 - Disclosure risks in longitudinally linked data and potential approaches for protection. Robin Mitra, Stephanie Blanchard, Caroline Tudor and Keith Spicer (*)
THURSDAY, 18 SEPTEMBER
Protection Using Privacy Models
Session Chair: Kris Muralidhar
- 9:00 - Improving the Utility of Differential Privacy via Univariate Microaggregation. David Sánchez, Josep Domingo-Ferrer and Sergio Martínez
- 9:25 - Differentially Private Exponential Random Graphs. Vishesh Karwa, Aleksandra Slavkovic and Pavel Krivitsky
- 9:50 - km-Anonymity for Continuous Data Using Dynamic Hierarchies. Olga Gkountouna, Sotiris Angeli, Athanasios Zigomitros, Manolis Terrovitis and Yannis Vassiliou
- 10:15 - Differentially-Private Logistic Regression for Detecting Multiple-SNP Association in GWAS Databases. Fei Yu, Michal Rybar, Caroline Uhler and Stephen E. Fienberg
10:40 - Coffee Break
Privacy-Preserving Protocols
Session Chair: Juan José Salazar
- 11:00 - Towards Secure and Practical Location Privacy through Private Equality Testing. Emmanouil Magkos, Panayiotis Kotzanikolaou, Marios Magioladitis, Spyros Sioutas and Vassilios S. Verykios
Remote Access
Session Chair: Peter Paul de Wolf
- 11:25 - Comparison of Two Remote Access Systems Recently Developed and Implemented in Australia. Christine O'Keefe, Phillip Gould and Tim Churches
Case Studies and Software I
Session Chair: Christine O’Keefe
- 11:50 - Controlled Shuffing, Statistical Confidentiality and Microdata Utility: a Successful Experiment with a 10% Household Sample of the 2011 Population Census of Ireland for the IPUMS-International Database. Robert McCaa, Krish Muralidhar, Rathindra Sarathy, Michael Comerford and Albert Esteve-Palos
- 12:15 - Balancing Confidentiality and Usability: Protecting Sensitive Data in the Caseof Inward Foreign AffiliaTes Statistics (FATS). Katri Soininvaara, Teemu Oinonen, Annu Nissinen
- 12:40 - Scenario Analysis of Privacy Attacks either on or using Genomic Data. Sahel Shariati Samani, Mark Elliot and Andrew Brass (*)
12:55 - Lunch
Case Studies and Software II
Session Chair: Natalie Shlomo
- 15:00 - Applicability of Confidentiality Methods to Personal and Business Data. Christine O'Keefe and Natalie Shlomo
- 15:25 - A French Anonymization Experiment with Health Data. Maxime Bergeat, Nora Cuppens-Boulahia, Frédéric Cuppens, Noémie Jess, Saïd Oulmakhzoune, Françoise Dupont, Gaël de Peretti (*)
- 15:40 - EUL to OGD: A Simulated Attack on Two Social Survey Datasets. Mark Elliot, Elaine Mackey, Susan O’Shea, Caroline Tudor, Keith Spicer (*)
- 15:55 - DDI Data Description Statistics Protection Software. Sebastian Kocar (*)
- 16:10 - Announcement: "Co-Utility" project.
16:15 - Coffee Break
16:45 - Guided visit to Eivissa (Meeting Point)
20:00 - Gala Dinner (Restaurant Location)
FRIDAY, 19 SEPTEMBER
Tabular Data Protection I
Session Chair: Sarah Giessing
- 9:00 - Enabling Statistical Analysis of Suppressed Tabular Data. Lawrence H. Cox
- 9:25 - Assessing the Information Loss of Controlled Adjustment Methods in Two-Way Tables. Jordi Castro and José A. González
- 9:50 - Further Developments with Perturbation Techniques to Protect Tabular Data. María Salomé Hernández-García and Juan José Salazar-González
- 10:15 - Comparison of Different Sensitivity Rules for Tabular Data and Presenting a New Rule -- the Interval Rule. Johan Bring and Qun Wang
10:40 - Coffee Break
Tabular Data Protection II
Session Chair: Larry Cox
- 11:00 - Pre-tabular Perturbation with Controlled Tabular Adjustment: Some Considerations. Sarah Giessing
- 11:25 - Measuring Disclosure Risk with Entropy in Population Based Frequency Tables. Laszlo Antal, Natalie Shlomo and Mark Elliot
- 11:50 - A CTA Model Based on the Huber Function. Jordi Castro
- 12:15 - Closing remarks
(*) - Short paper in USB proceedings