Enhanced Membership Inference Attacks against Machine Learning Models. (arXiv:2111.09679v4 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2111.09679

How much does a machine learning algorithm leak about its training data, and
why? Membership inference attacks are used as an auditing tool to quantify this
leakage. In this paper, we present a comprehensive \textit{hypothesis testing
framework} that enables us not only to formally express the prior work in a
consistent way, but also to design new membership inference attacks that use
reference models to achieve a significantly higher power (true positive rate)
for any (false positive rate) error. More …

attacks machine machine learning machine learning models