Privacy-Preserving Data Mining Techniques: Survey and Challenges - Discrimination and Privacy in the Information Society - page 201

Chapter 11
Privacy-Preserving Data Mining Techniques:
Survey and Challenges
Stan Matwin *
Abstract. This chapter presents a brief summary and review of Privacy-preserving
Data Mining (PPDM). The review of the existing approaches is structured along a
tentative taxonomy of PPDM as a field. The main axes of this taxonomy specify
what kind of data is being protected, and what is the ownership of the data (centra-
lized or distributed). We comment on the relationship between PPDM and pre-
venting discriminatory use of data mining techniques. We round up the chapter by
discussing some of the new, arising challenges before PPDM as a field.
11.1 Introduction
Exponential growth of information and communication technologies in the last
thirty years, and their deep penetration of every segment of the society, raised no
fundamental opposition or critique. There is, however, social sensitivity related to
one aspect of those technologies: it is their potentially negative influence on per-
sonal privacy. Data that - in themselves - are not jeopardizing individual privacy,
can be instantaneously and freely combined with other data and used in sophisti-
cated inference. New information produced in that manner becomes available to
parties completely unknown to the original “owner” of the data. This has been apt-
ly described by James Moor as the “greased data” phenomenon (Moor 2004), and
it is only possible thanks to information technology. It is therefore reasonable to
look for technological solutions to potential privacy breaches that are enabled by
modern advances in information and data transmission. In the eyes of some, there
is a “moral imperative” for Computer Science as a field: at least some researchers
should work on finding solutions to problems that the field itself may have
exacerbated. Research focusing on privacy aspects of data mining is known as
Privacy-Preserving Data Mining (PPDM). This article provides a high-level re-
view of the accomplishments of this research, as well as a brief discussion of the