mlsanityData to 13 Oct 2026

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

arXiv 2211.01656 ↗First posted 3 Nov 2022cs.LG cs.AI cs.CRcited by 4

Not on the map. Why?

Abstract (arXiv)

TREs are widely, and increasingly used to support statistical analysis of sensitive data across a range of sectors (e.g., health, police, tax and education) as they enable secure and transparent research whilst protecting data confidentiality. 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.

Key facts. Cited by 4 papers in the map (data through 13 Oct 2026). Builds on 12 of its 51 references that are in the map. First posted on arXiv 3 Nov 2022.

Builds on

12 of 51 references.

References · 12

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,143
  2. 2021Membership Inference Attacks From First Principlescited by 872
  3. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 711
  4. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 497
  5. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 122
  6. 2019Understanding artificial intelligence ethics and safetycited by 68
  7. 2018Algorithms that Remember: Model Inversion Attacks and Data Protection Lawcited by 55
  8. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  9. 2022A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learningcited by 27
  10. 2020The Limits of Differential Privacy (and its Misuse in Data Release and Machine Learning)cited by 22
  11. 2019Design choices for productive, secure, data-intensive research at scale in the cloudcited by 3
  12. 2021Machine Learning Models Disclosure from Trusted Research Environments (TRE), Challenges and Opportunitiescited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 1; 2026: 2.

4 papers.

  1. 2022Safe machine learning model release from Trusted Research Environments: The SACRO-ML packagecited by 2
  2. 2025A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attackcited by 2
  3. 2026Foresight-England: Development of a National-Scale Generative AI Model of Electronic Health Records for Medical Event Prediction across the COVID-19 Pandemiccited by 0
  4. 2026Predicting Privacy Leakage from Weight Spectral Densitycited by 0