Paper ID: 2212.01233 • Published Dec 2, 2022

Safe machine learning model release from Trusted Research Environments: The SACRO-ML package

Jim Smith, Richard J. Preen, Andrew McCarthy, Maha Albashir, Alba Crespi-Boixader, Shahzad Mumtaz, James Liley, Simon...
TL;DR
Get AI-generated summaries with premium
Get AI-generated summaries with premium
We present SACRO-ML, an integrated suite of open source Python tools to facilitate the statistical disclosure control (SDC) of machine learning (ML) models trained on confidential data prior to public release. SACRO-ML combines (i) a SafeModel package that extends commonly used ML models to provide ante-hoc SDC by assessing the vulnerability of disclosure posed by the training regime; and (ii) an Attacks package that provides post-hoc SDC by rigorously assessing the empirical disclosure risk of a model through a variety of simulated attacks after training. The SACRO-ML code and documentation are available under an MIT license at this https URL