arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.01233cs.LGcs.CRcs.IR
收藏

从可信研究环境安全发布机器学习模型:SACRO-ML 工具包

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

School of Computer Science, University of the West of England(西英格兰大学计算机科学学院);School of Medicine, University of Dundee(邓迪大学医学院);Department of Mathematical Sciences, University of Durham(达勒姆大学数学科学系);Department of Physics, King’s College London(伦敦国王学院物理系);NHS National Services Scotland(苏格兰国家健康服务)

Jim Smith, Richard J. Preen, Andrew McCarthy, Maha Albashir, Alba Crespi-Boixader, Shahzad Mumtaz, Christian Cole, James Liley, Jost Migenda, Simon Rogers, Yola Jones

AI总结:

本研究推出开源Python工具集SACRO-ML,通过SafeModel包的事前风险评估与Attacks包的事后模拟攻击验证,实现可信研究环境中机密数据训练的机器学习模型发布前的统计披露控制。

摘要:

我们推出 SACRO-ML,这是一套集成的开源 Python 工具集,用于在基于机密数据训练的机器学习(ML)模型公开发布前,对其实施统计披露控制(SDC)。SACRO-ML 包含两部分:一是 SafeModel 包,它对常用 ML 模型进行扩展,通过评估训练机制带来的披露风险实现事前 SDC;二是 Attacks 包,通过训练后开展多种模拟攻击,严格评估模型的实证披露风险,以此实现事后 SDC。SACRO-ML 的代码和文档基于 MIT 许可证发布,可在 https://github.com/AI-SDC/SACRO-ML 获取。

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑