< Retour au sommaire
Privacy-Preserving Record Linkage: Technological, Ethical, Adversarial, and Analytical Developments
Dinusha Vatsalan le
Lieu: bât 862, Amphis 33-34
Suivre en visio
Abstract
Personal Identifiable Information (PII) about individuals, such as customers,
taxpayers, patients, and mobile application users, is increasingly collected and
linked across disparate data sources to enable customized, high-quality, and
timely analytical services in a variety of applications. Examples include health
applications such as similar patient matching for clinical trials and rare
disease patients counting for adequate awareness and funding, business
applications that collect personal information to support customer contracts and
improve business operations, governments services that collect personal data for
national security and public safety, and cybersecurity applications such as
tracking the number of unique views of social media posts. The data (PII) needed
for the linkage analytics is, however, often personal and sensitive, and needs
to be processed using privacy-preserving techniques. Known as privacy-preserving
record linkage (PPRL), a large body of work has been conducted in this research
topic. I have been conducting research and development in PPRL addressing the
key challenges of enhancing computational efficiency, linkage quality, and
privacy guarantees of linkage. In this talk, I will present our work on PPRL and
an outlook to the next directions of research.