Speaker: Professor Vicenç Torra, Hamilton Institute / Maynooth University Department of Computer Science
Title: "On data privacy for machine learning"
Abstract: Data privacy studies and develops methods and tools for avoiding the
disclosure of sensitive information. Privacy models, computational
definitions of privacy, permit to define when data and models are
considered safe with respect to disclosure. Some can be seen as Boolean
properties, other as quantitative measurements). Data protection
mechanisms are defined to be compliant with privacy models, and to achieve
a good trade-off between disclosure risk and data utility.
In this talk I will give an overview of privacy models and disclosure risk
measures. I will use this overview to place our work in the area. This
includes masking methods and disclosure risk assessment. I will discuss
the use of machine learning for disclosure risk assessment, and present
our research related to data privacy for machine learning.