1 code implementation • 2 Dec 2022 • Jim Smith, Richard J. Preen, Andrew McCarthy, Alba Crespi-Boixader, James Liley, Simon Rogers
We present AI-SDC, an integrated suite of open source Python tools to facilitate Statistical Disclosure Control (SDC) of Machine Learning (ML) models trained on confidential data prior to public release.
no code implementations • 3 Nov 2022 • Emily Jefferson, James Liley, Maeve Malone, Smarti Reel, Alba Crespi-Boixader, Xaroula Kerasidou, Francesco Tava, Andrew McCarthy, Richard Preen, Alberto Blanco-Justicia, Esma Mansouri-Benssassi, Josep Domingo-Ferrer, Jillian Beggs, Antony Chuter, Christian Cole, Felix Ritchie, Angela Daly, Simon Rogers, Jim Smith
This is a complex topic, and it is unreasonable to expect all TREs to be aware of all risks or that TRE researchers have addressed these risks in AI-specific training.
no code implementations • 13 Feb 2022 • Sami Haidar-Wehbe, Samuel R Emerson, Louis J M Aslett, James Liley
To address this, we propose updating using a `holdout set' - a subset of the population that does not receive interventions guided by the risk score.
1 code implementation • 22 Oct 2020 • James Liley, Samuel R Emerson, Bilal A Mateen, Catalina A Vallejos, Louis J M Aslett, Sebastian J Vollmer
Recent discussions have highlighted potential problems in the updating of a predictive score for a binary outcome when an existing predictive score forms part of the standard workflow, driving interventions.