Generative models trained with Differential Privacy (DP) can be used to generate synthetic data while minimizing privacy risks. We analyze the impact of DP on these models vis-a-vis underrepresented classes/subgroups of data, specifically, studying: 1) the size of classes/subgroups in the synthetic data, and 2) the accuracy of classification tasks run on them. We also evaluate the effect of various levels of imbalance and privacy budgets. Our analysis uses three state-of-the-art DP models (PrivBayes, DP-WGAN, and PATE-GAN) and shows that DP yields opposite size distributions in the generated synthetic data. It affects the gap between the majority and minority classes/subgroups; in some cases by reducing it (a "Robin Hood" effect) and, in others, by increasing it (a "Matthew" effect). Either way, this leads to (similar) disparate impacts on the accuracy of classification tasks on the synthetic data, affecting disproportionately more the underrepresented subparts of the data. Consequently, when training models on synthetic data, one might incur the risk of treating different subpopulations unevenly, leading to unreliable or unfair conclusions.

Summary: Advances in genome sequencing and genomics research are bringing us closer to a new era of personalized medicine, where healthcare can be tailored to the individual's genetic makeup and to more effective diagnosis and treatment of rare genetic diseases. Much of this progress depends on collaborations and access to data, thus, a number of initiatives have been introduced to support seamless data sharing. Among these, the Global Alliance for Genomics and Health has developed and operates a platform, called Matchmaker Exchange (MME), which allows researchers to perform queries for rare genetic disease discovery over multiple federated databases. Queries include gene variations which are linked to rare diseases, and the ability to find other researchers that have seen or have interest in those variations is extremely valuable. Nonetheless, in some cases, researchers may be reluctant to use the platform since the queries they make (thus, what they are working on) are revealed to other researchers, and this creates concerns with respect to privacy and competitive advantage. In this paper, we present AnoniMME, a framework geared to enable anonymous queries within the MME platform. The framework, building on a cryptographic primitive called Reverse Private Information Retrieval, let researchers anonymously query the federated platform, in a multi-server setting-specifically, they write their query, along with a public encryption key, anonymously in a public database. Responses are also supported, so that other researchers can respond to queries by providing their encrypted contact details. Availability and implementation: https://github.com/bristena-op/AnoniMME.