Projects per year
There is an increasing desire from academia and industry to train AI models in TREs. The field of AI is developing quickly with applications including spotting human errors, streamlining processes, task automation and decision support. These complex AI models require more information to describe and reproduce, increasing the possibility that sensitive personal data can be inferred from such descriptions. TREs do not have mature processes and controls against these risks. 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.
GRAIMATTER has developed a draft set of usable recommendations for TREs to guard against the additional risks when disclosing trained AI models from TREs. The development of these recommendations has been funded by the GRAIMATTER UKRI DARE UK sprint research project. This version of our recommendations was published at the end of the project in September 2022. During the course of the project, we have identified many areas for future investigations to expand and test these recommendations in practice. Therefore, we expect that this document will evolve over time.
The GRAIMATTER DARE UK sprint project has also developed a minimal viable product (MVP) as a suite of attack simulations that can be applied by TREs and can be accessed here (https://github.com/AI-SDC/AI-SDC).
If you would like to provide feedback or would like to learn more, please contact Smarti Reel (email@example.com) and Emily Jefferson (firstname.lastname@example.org).
The summary of our recommendations for a general public audience can be found at DOI: 10.5281/zenodo.7089514
FingerprintDive into the research topics of 'GRAIMATTER Green Paper: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)'. Together they form a unique fingerprint.
- 1 Finished
Green Paper: Disclosure Control Of Al Algorithms From TREs (GRAIMATTER) lead: University of Dundee other instns: National Services Scotland, University of the West England UWE - Bristol, University of Edinburgh, URV (Spain)
4/01/22 → 31/08/22
- 1 Conference contribution
Jefferson, E., Cole, C., Crespi Boixader, A., Rogers, S., Roche, M., Ritchie, F., Smith, J., Tava, F., Daly, A., Beggs, J. & Chuter, A., 25 Aug 2022, Conference Proceedings for International Population Data Linkage Conference 2022. 3 ed. Vol. 7.
Research output: Chapter in Book/Report/Conference proceeding › Conference contributionOpen Access
- 1 Public engagement and outreach - media article or participation
GRAIMATTER Public Summary: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)
Emily Jefferson (Member), Felix Ritchie (Member), Jillian Beggs (Member), Antony Chuter (Member), Smarti Reel (Member), Alba Crespi Boixader (Member), Francesco Tava (Member), Esma Mansouri-Benssassi (Member), Maeve Malone (Member), Christian Cole (Member), Angela Daly (Member), Simon Rogers (Member) & Jim Smith (Member)21 Sept 2022
Activity: Other activity types › Public engagement and outreach - media article or participation