Towards Fair Classification against Poisoning Attacks. (arXiv:2210.09503v1 [cs.LG])

Fair classification aims to stress the classification models to achieve the
equality (treatment or prediction quality) among different sensitive groups.
However, fair classification can be under the risk of poisoning attacks that
deliberately insert malicious training samples to manipulate the trained
classifiers' performance. In this work, we study the poisoning scenario where
the attacker can insert a small fraction of samples into training data, with
arbitrary sensitive attributes as well as other predictive features. We
demonstrate that the fairly trained …

attacks classification fair poisoning