R\'enyi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration. (arXiv:2312.13985v1 [cs.CR])

Pufferfish privacy is a flexible generalization of differential privacy that
allows to model arbitrary secrets and adversary's prior knowledge about the
data. Unfortunately, designing general and tractable Pufferfish mechanisms that
do not compromise utility is challenging. Furthermore, this framework does not
provide the composition guarantees needed for a direct use in iterative machine
learning algorithms. To mitigate these issues, we introduce a R\'enyi
divergence-based variant of Pufferfish and show that it allows us to extend the
applicability of the Pufferfish …

adversary amplification compromise data differential privacy framework general knowledge noise privacy secrets utility