Safe machine learning model release from Trusted Research Environments: The SACRO-ML package
This addresses the need for secure model release from Trusted Research Environments, offering a practical solution for researchers handling sensitive data.
They tackled the problem of safely releasing machine learning models trained on confidential data by developing SACRO-ML, an open-source Python package that provides tools for statistical disclosure control, resulting in a suite that assesses vulnerability before training and empirical risk after training.
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