Algorithmic fairness and privacy are essential pillars of trustworthy machine
learning. Fair machine learning aims at minimizing discrimination against
protected groups by, for example, imposing a constraint on models to equalize
their behavior across different groups. This can subsequently change the
influence of training data points on the fair model, in a disproportionate way.
We study how this can change the information leakage of the model about its
training data. We analyze the privacy risks of group fairness (e.g., equalized
odds) through the lens of membership inference attacks: inferring whether a
data point is used for training a model. We show that fairness comes at the
cost of privacy, and this cost is not distributed equally: the information
leakage of fair models increases significantly on the unprivileged subgroups,
which are the ones for whom we need fair learning. We show that the more biased
the training data is, the higher the privacy cost of achieving fairness for the
unprivileged subgroups will be. We provide comprehensive empirical analysis for
general machine learning algorithms.

Go to Source of this post
Author Of this post: <a href="">Hongyan Chang</a>, <a href="">Reza Shokri</a>

By admin