Work

Rmind: A Tool for Cryptographically Secure Statistical Analysis

Year: 2016

Type: article

Abstract: Secure multi-party computation is a practical cryptographic method for processing confidential data. Research progress has led to its use in privacy-preserving statistical analysis. Implementations of simple statistical analysis functions have been published, but no comprehensive tool has been built. We describe and implement a suite of most used statistical analysis functions in the privacy-preserving setting including simple statistics, t-test, chi-squared test, Wilcoxon tests and linear regression. We give descriptions of the privacy-preserving algorithms and benchmark results that show an order of magnitude improvement over previous work.

Source: IEEE Transactions on Dependable and Secure Computing

DOI: 10.1109/tdsc.2016.2587623

Authors: Dan Bogdanov, Liina Kamm, Sven Laur, Ville Sokk

Institutions: Cybernetica (Estonia), University of Tartu

Language: English

Topic: Cryptography and Data Security

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $2,645

Funders: European Commission, Eesti Teadusagentuur, Seventh Framework Programme, European Regional Development Fund