Dealing with statistical data
To this end, the capabilities and limitations of advanced security and privacy enhancing technologies are studied and translated into training courses for lecturers and study materials for students. Currently, the study focuses on how to deal with statistical disclosure risks, inflicting personal data leakages during collection, processing and sharing data. Dealing with statistical data risks is a challenge nowadays because of, among other, a rapid growth of data volume, variety, velocity ... and a vast amount of background information available to data receivers and adversaries. The first factor makes it difficult to detect potential privacy (or information sensitivity) issues hidden in a dataset. The second factor makes it difficult to assess the potential risks when a given dataset is linked to other datasets (i.e., combined with background information). Specifically, the results of this study are continuously being embedded in a course within the data science minor at CMI.
The study within this project focuses also on investigating those design and engineering methodologies that enable realising such privacy protecting and secure systems. To this end, the study aims at developing an overarching methodology that integrates the capabilities of design thinking and requirement engineering methods.