GRAIMATTER Public Summary: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)

Felix Ritchie; Jillian Beggs; Antony Chuter; Smarti Reel; Alba Crespi-Boixader; Xaroula Kerasidou; Francesco Tava; Andrew McCarthy; Richard Preen; Alberto Blanco-Justicia; Esma Mansouri-Benssassi; Josep Domingo-Ferrer; James Liley; Maeve Malone; Christian Cole; Angela Daly; Simon Rogers; Jim Smith; Emily Jefferson

doi:10.5281/ZENODO.7089514

GRAIMATTER Public Summary: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)

Felix Ritchie
, Jillian Beggs
, Antony Chuter
, Smarti Reel
, Alba Crespi-Boixader
, Xaroula Kerasidou
, Francesco Tava
, Andrew McCarthy
, Richard Preen
, Alberto Blanco-Justicia
, Esma Mansouri-Benssassi
, Josep Domingo-Ferrer
, James Liley
, Maeve Malone
, Christian Cole
, Angela Daly
, Simon Rogers
, Jim Smith
, Emily Jefferson

Research output: Book/Report › Commissioned report

Abstract

GRAIMATTER has developed a draft set of usable recommendations for TREs to guard against the additional risks when disclosing trained AI models from TREs. This report provides a summary of our recommendations for a general public audience. The detailed Green Paper on recommendations can be found at DOI: 10.5281/zenodo.7089491 If you would like to provide feedback or would like to learn more, please contact Smarti Reel ([email protected] Jefferson ([email protected]).

Original language	English
Publisher	Zenodo
Number of pages	8
DOIs	https://doi.org/10.5281/ZENODO.7089514
Publication status	Published - 21 Sept 2022

Access to Document

10.5281/ZENODO.7089514Licence: CC BY

Final Published VersionFinal published version, 414 KBLicence: CC BY

Health Informatics Centre
Health and Clinical Services
Facility/equipment: Facility

Cite this

Ritchie, F., Beggs, J., Chuter, A., Reel, S., Crespi-Boixader, A., Kerasidou, X., Tava, F., McCarthy, A., Preen, R., Blanco-Justicia, A., Mansouri-Benssassi, E., Domingo-Ferrer, J., Liley, J., Malone, M., Cole, C., Daly, A., Rogers, S., Smith, J., & Jefferson, E. (2022). GRAIMATTER Public Summary: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs). Zenodo. https://doi.org/10.5281/ZENODO.7089514

@book{ab4e8e2a6e3e4415adeb27f958b3584a,

title = "GRAIMATTER Public Summary: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)",

abstract = "GRAIMATTER has developed a draft set of usable recommendations for TREs to guard against the additional risks when disclosing trained AI models from TREs. This report provides a summary of our recommendations for a general public audience. The detailed Green Paper on recommendations can be found at DOI: 10.5281/zenodo.7089491 If you would like to provide feedback or would like to learn more, please contact Smarti Reel ([email protected] Jefferson ([email protected]).",

author = "Felix Ritchie and Jillian Beggs and Antony Chuter and Smarti Reel and Alba Crespi-Boixader and Xaroula Kerasidou and Francesco Tava and Andrew McCarthy and Richard Preen and Alberto Blanco-Justicia and Esma Mansouri-Benssassi and Josep Domingo-Ferrer and James Liley and Maeve Malone and Christian Cole and Angela Daly and Simon Rogers and Jim Smith and Emily Jefferson",

year = "2022",

month = sep,

day = "21",

doi = "10.5281/ZENODO.7089514",

language = "English",

publisher = "Zenodo",

address = "Switzerland",

}

Ritchie, F, Beggs, J, Chuter, A, Reel, S , Crespi-Boixader, A, Kerasidou, X, Tava, F, McCarthy, A, Preen, R, Blanco-Justicia, A, Mansouri-Benssassi, E, Domingo-Ferrer, J, Liley, J, Malone, M , Cole, C , Daly, A, Rogers, S, Smith, J & Jefferson, E 2022, GRAIMATTER Public Summary: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs). Zenodo. https://doi.org/10.5281/ZENODO.7089514

TY - BOOK

T1 - GRAIMATTER Public Summary: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)

AU - Ritchie, Felix

AU - Beggs, Jillian

AU - Chuter, Antony

AU - Reel, Smarti

AU - Crespi-Boixader, Alba

AU - Kerasidou, Xaroula

AU - Tava, Francesco

AU - McCarthy, Andrew

AU - Preen, Richard

AU - Blanco-Justicia, Alberto

AU - Mansouri-Benssassi, Esma

AU - Domingo-Ferrer, Josep

AU - Liley, James

AU - Malone, Maeve

AU - Cole, Christian

AU - Daly, Angela

AU - Rogers, Simon

AU - Smith, Jim

AU - Jefferson, Emily

PY - 2022/9/21

Y1 - 2022/9/21

N2 - GRAIMATTER has developed a draft set of usable recommendations for TREs to guard against the additional risks when disclosing trained AI models from TREs. This report provides a summary of our recommendations for a general public audience. The detailed Green Paper on recommendations can be found at DOI: 10.5281/zenodo.7089491 If you would like to provide feedback or would like to learn more, please contact Smarti Reel ([email protected] Jefferson ([email protected]).

AB - GRAIMATTER has developed a draft set of usable recommendations for TREs to guard against the additional risks when disclosing trained AI models from TREs. This report provides a summary of our recommendations for a general public audience. The detailed Green Paper on recommendations can be found at DOI: 10.5281/zenodo.7089491 If you would like to provide feedback or would like to learn more, please contact Smarti Reel ([email protected] Jefferson ([email protected]).

U2 - 10.5281/ZENODO.7089514

DO - 10.5281/ZENODO.7089514

M3 - Commissioned report

BT - GRAIMATTER Public Summary: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)

PB - Zenodo

ER -

GRAIMATTER Public Summary: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)

Abstract

Access to Document

Fingerprint

Equipment

Health Informatics Centre

Cite this