We review the use of differential privacy (DP) for privacy protection in machine learning
(ML). We show that, driven by the aim of preserving the accuracy of the learned models, DP …

The increasing volume of personal and sensitive data being harvested by data controllers
makes it increasingly necessary to use the cloud not just to store the data, but also to …

Decisions based on algorithmic, machine learning models can be unfair, reproducing biases
in historical data used to train them. While computational techniques are emerging to …

Privacy and data protection constitute core values of individuals and of democratic societies.
There have been decades of debate on how those values-and legal obligations-can be …

We present a novel benchmark and associated evaluation metrics for assessing the
performance of text anonymization methods. Text anonymization, defined as the task of …

Cities are growing steadily, and the process of urbanization is a common trend in the world.
Although cities are getting bigger, they are not necessarily getting better. With the aim to …

Data holders can produce synthetic versions of data sets when concerns about potential
disclosure restrict the availability of the original records. The paper is concerned with …

Background There has been growing interest in data synthesis for enabling the sharing of
data for secondary analysis; however, there is a need for a comprehensive privacy risk …

Sensitive personal data are created in many application domains, and there is now an
increasing demand to share, integrate, and link such data within and across organisations in …

Stochastic rounding (SR) randomly maps a real number x to one of the two nearest values in
a finite precision number system. The probability of choosing either of these two numbers is …