Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage. (arXiv:2308.04341v1 [cs.LG])

Machine learning models are increasingly utilized across impactful domains to
predict individual outcomes. As such, many models provide algorithmic recourse
to individuals who receive negative outcomes. However, recourse can be
leveraged by adversaries to disclose private information. This work presents
the first attempt at mitigating such attacks. We present two novel methods to
generate differentially private recourse: Differentially Private Model (DPM)
and Laplace Recourse (LR). Using logistic regression classifiers and real world
and synthetic datasets, we find that DPM and …

adversaries data data leakage domains information machine machine learning machine learning models outcomes predict private training work