当前位置: X-MOL 学术BMC Med. Genomics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Privacy-preserving semi-parallel logistic regression training with fully homomorphic encryption.
BMC Medical Genomics ( IF 2.1 ) Pub Date : 2020-07-21 , DOI: 10.1186/s12920-020-0723-0
Sergiu Carpov 1, 2 , Nicolas Gama 2 , Mariya Georgieva 2, 3 , Juan Ramon Troncoso-Pastoriza 3
Affiliation  

Privacy-preserving computations on genomic data, and more generally on medical data, is a critical path technology for innovative, life-saving research to positively and equally impact the global population. It enables medical research algorithms to be securely deployed in the cloud because operations on encrypted genomic databases are conducted without revealing any individual genomes. Methods for secure computation have shown significant performance improvements over the last several years. However, it is still challenging to apply them on large biomedical datasets. The HE Track of iDash 2018 competition focused on solving an important problem in practical machine learning scenarios, where a data analyst that has trained a regression model (both linear and logistic) with a certain set of features, attempts to find all features in an encrypted database that will improve the quality of the model. Our solution is based on the hybrid framework Chimera that allows for switching between different families of fully homomorphic schemes, namely TFHE and HEAAN. Our solution is one of the finalist of Track 2 of iDash 2018 competition. Among the submitted solutions, ours is the only bootstrapped approach that can be applied for different sets of parameters without re-encrypting the genomic database, making it practical for real-world applications. This is the first step towards the more general feature selection problem across large encrypted databases.

中文翻译:

具有完全同态加密的隐私保护半并行逻辑回归训练。

在基因组数据上,更普遍地在医学数据上,保护隐私的计算是创新,挽救生命的研究对全球人口产生积极且平等影响的关键路径技术。它使医学研究算法可以安全地部署在云中,因为在不透露任何单个基因组的情况下进行了加密基因组数据库的操作。在过去的几年中,用于安全计算的方法已显示出显着的性能改进。但是,将它们应用于大型生物医学数据集仍然具有挑战性。iDash 2018竞赛的HE Track专注于解决实际机器学习场景中的一个重要问题,在该场景中,数据分析师训练了具有某些功能的回归模型(线性和逻辑模型),尝试在加密的数据库中查找所有可提高模型质量的功能。我们的解决方案基于混合框架Chimera,该框架允许在完全同构方案的不同族(即TFHE和HEAAN)之间进行切换。我们的解决方案是iDash 2018竞赛第二轮决赛入围者之一。在提交的解决方案中,我们的方法是唯一可用于不同参数集的自举方法,而无需重新加密基因组数据库,从而使其在实际应用中实用。这是跨大型加密数据库解决更一般特征选择问题的第一步。即TFHE和HEAAN。我们的解决方案是iDash 2018竞赛第二轮决赛入围者之一。在提交的解决方案中,我们的方法是唯一可用于不同参数集的自举方法,而无需重新加密基因组数据库,从而使其在实际应用中实用。这是跨大型加密数据库解决更一般特征选择问题的第一步。即TFHE和HEAAN。我们的解决方案是iDash 2018竞赛第二轮决赛入围者之一。在提交的解决方案中,我们的方法是唯一可用于不同参数集的自举方法,而无需重新加密基因组数据库,从而使其在实际应用中实用。这是跨大型加密数据库解决更一般特征选择问题的第一步。
更新日期:2020-07-21
down
wechat
bug