Collaborative Drug Discovery: Inference-level Data Protection Perspective

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 pl...

Full description

Saved in:
Bibliographic Details
Main Authors Pejo, Balazs, Remeli, Mina, Arany, Adam, Galtier, Mathieu, Acs, Gergely
Format Journal Article
LanguageEnglish
Published 13.05.2022
Subjects
Computer Science - Cryptography and Security
Computer Science - Learning
Online AccessGet full text

Cover

More Information
Summary: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.
DOI:10.48550/arxiv.2205.06506