Authors:
Marijn Janssen
1
;
Anneke Zuiderwijk
1
and
Amr M. T. Ali- Eldin
2
Affiliations:
1
TBM - Delft University of Technology,, Netherlands
;
2
Leiden Institute of Advanced Computer Science, Leiden University,, Netherlands
Keyword(s):
Open Data, Open Government Data, Privacy, Risk, Data Release, Data Mining, Scoring Systems.
Abstract:
While the opening of data has become a common practice for both governments and companies, many datasets
are still not published since they might violate privacy regulations. The risk on privacy violations is a factor
that often blocks the publication of data and results in a reserved attitude of governments and companies.
Additionally, even published data, which might seem privacy compliant, can violate user privacy due to the
leakage of real user identities. This paper proposes a privacy risk scoring model for open data architectures to
analyse and reduce the risks associated with the opening of data. The key elements consist of a new set of
open data attributes reflecting privacy risks versus benefits trades-offs. Further, these attributes are evaluated
using a decision engine and a scoring matrix intro a privacy risk indicator (PRI) and a privacy risk mitigation
measure (PRMM). Privacy Risk Indicator (PRI) represents the predicted value of privacy risks associated
with opening su
ch data and privacy risk mitigation measures represent the measurements need to be applied
on the data to avoid the expected privacy risks. The model is exemplified through five real use cases
concerning open datasets.
(More)