Privacy issues are an undying obstacle to the real-world implementation of
information systems, from online retailers, to social networks, to smart
home technology. Existing solutions to these privacy issues involve giving
users more control over, and more information about, the privacy settings
provided by these systems. In this talk I will argue that these solutions fail
when users with limited cognitive resources encounter systems with
complex and far-reaching privacy implications. I will subsequently discuss
a novel human-centric solution to improve users' privacy decisions:
User-Tailored Privacy. User-Tailored Privacy is an approach to privacy that
measures users’ privacy-related characteristics and behaviors, uses this
as input to model their privacy preferences, and then provides them with
adaptive privacy decision support. In effect, it applies data science as a
means to support users’ privacy decisions.