Drynx: Decentralized, Secure, Verifiable System for Statistical Queries and Machine Learning on Distributed Datasets

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.

Leveraging Data Science To Combat COVID-19: A Comprehensive Review

“…For example, MedCo [217] uses homomorphic encryption to allow sites to federate datasets with privacy guarantees. Drynx [218] supports privacy-conscious statistical analysis on distributed datasets. This links closely into the availability of data (see §VI-A), as often data can only be shared when robust privacy guarantees are in place.…”

Leveraging Data Science To Combat COVID-19: A Comprehensive Review

“…For example, MedCo [203] uses homomorphic encryption to allow sites to federate datasets with privacy guarantees. Drynx [204] supports privacyconscious statistical analysis on distributed datasets. This links closely into the quality of data (see §VI-A), as often data can only be shared when robust privacy guarantees are in place.…”

Helen: Maliciously Secure Coopetitive Learning for Linear Models

“…Most of these works also do not address the malicious setting. Recent work has also explored secure learning and analytics using separate compute nodes and blockchains [36,35]. The setup is different from that of Helen where we assume that the data providers are malicious and are also performing and verifying the computation.…”