Pharmaceutical industry can better leverage its data assets to virtualize drug discovery through a collaborative machine learning platform. On the other hand, there are non-negligible risks stemming from the unintended leakage of participants' training data, hence, it is essential for such a platform to be secure and privacy-preserving. This paper describes a privacy risk assessment for collaborative modeling in the preclinical phase of drug discovery to accelerate the selection of promising drug candidates. After a short taxonomy of state-of-the-art inference attacks we adopt and customize several to the underlying scenario. Finally we describe and experiments with a handful of relevant privacy protection techniques to mitigate such attacks.
@article{arxiv.2205.06506,
title = {Collaborative Drug Discovery: Inference-level Data Protection Perspective},
author = {Balazs Pejo and Mina Remeli and Adam Arany and Mathieu Galtier and Gergely Acs},
journal= {arXiv preprint arXiv:2205.06506},
year = {2022}
}