Drynx: Decentralized, Secure, Verifiable System for Statistical Queries and Machine Learning on Distributed Datasets
Preprint
Abstract
Data sharing has become of primary importance in many domains such as big-data analytics, economics and medical research, but remains difficult to achieve when the data are sensitive. In fact, sharing personal information requires individuals' unconditional consent or is often simply forbidden for privacy and security reasons. In this paper, we propose Drynx, a decentralized system for privacy-conscious statistical analysis on distributed datasets. Drynx relies on a set of computing nodes to enable the computation of statistics such as standard deviation or extrema, and the training and evaluation of machine-learning models on sensitive and distributed data. To ensure data confidentiality and the privacy of the data providers, Drynx combines interactive protocols, homomorphic encryption, zero-knowledge proofs of correctness, and differential privacy. It enables an efficient and decentralized verification of the input data and of all the system's computations thus provides auditability in a strong adversarial model in which no entity has to be individually trusted. Drynx is highly modular, dynamic and parallelizable. Our evaluation shows that it enables the training of a logistic regression model on a dataset (12 features and 600,000 records) distributed among 12 data providers in less than 2 seconds. The computations are distributed among 6 computing nodes, and Drynx enables the verification of the query execution's correctness in less than 22 seconds.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- High-Precision Privacy-Preserving Real-Valued Function Evaluation2018
- MedCo: Enabling Secure and Privacy-Preserving Exploration of Distributed Clinical and Genomic DataIEEE/ACM Transactions on Computational Biology and Bioinformatics, 2018
- Private Information Retrieval for Secure Distributed Storage SystemsIEEE Transactions on Information Forensics and Security, 2018
- Privacy-Preserving Indexing and Query Processing for Secure Dynamic Cloud StorageIEEE Transactions on Information Forensics and Security, 2018
- Privacy-Preserving Deep Learning via Additively Homomorphic EncryptionIEEE Transactions on Information Forensics and Security, 2017
- Blockchain distributed ledger technologies for biomedical and health care applicationsJournal of the American Medical Informatics Association, 2017
- Achieving an effective, scalable and privacy-preserving data sharing service in cloud computingComputers & Security, 2014
- High-speed high-security signaturesJournal of Cryptographic Engineering, 2012
- The Patient-Centered Outcomes Research Institute (PCORI) National Priorities for Research and Initial Research AgendaJAMA, 2012
- Heart rate distribution and predictors of increased heart rate among French hypertensive patients with stable coronary artery disease. Data from the LHYCORNE cohortArchives of Cardiovascular Diseases, 2009