Safe machine learning model release from Trusted Research Environments: The SACRO-ML package

2022/12/02 by Richard J. Preen, Smith, Jim, Preen, Richard J. +13
Computer Science · Medicine · #Adversarial Robustness in Machine Learning #Artificial Intelligence in Healthcare and Education #Cryptography and Security (cs.CR) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2212.01233

openalex publication_date 2022/12/02 · openalex created_date 2022/12/19 · openalex updated_date 2026/07/28

Abstract

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

Related

• Machine Learning Models Disclosure from Trusted Research Environments (TRE), Challenges and Opportunities
• ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learning
• ML-Leaks: Model and Data Independent Membership Inference Attacks and\n Defenses on Machine Learning Models
• Green Lighting ML: Confidentiality, Integrity, and Availability of Machine Learning Systems in Deployment
• Confidential Machine Learning on Untrusted Platforms: A Survey