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 https://github.com/AI-SDC/SACRO-ML
Cite
@article{arxiv.2212.01233,
title = {Safe machine learning model release from Trusted Research Environments: The SACRO-ML package},
author = {Jim Smith and Richard J. Preen and Andrew McCarthy and Maha Albashir and Alba Crespi-Boixader and Shahzad Mumtaz and Christian Cole and James Liley and Jost Migenda and Simon Rogers and Yola Jones},
journal= {arXiv preprint arXiv:2212.01233},
year = {2025}
}