Baldur Kubo - Academia.edu (original) (raw)
Uploads
Papers by Baldur Kubo
Proceedings on Privacy Enhancing Technologies, 2016
We describe the use of secure multi-party computation for performing a large-scale privacy-preser... more We describe the use of secure multi-party computation for performing a large-scale privacy-preserving statistical study on real government data. In 2015, statisticians from the Estonian Center of Applied Research (CentAR) conducted a big data study to look for correlations between working during university studies and failing to graduate in time. The study was conducted by linking the database of individual tax payments from the Estonian Tax and Customs Board and the database of higher education events from the Ministry of Education and Research. Data collection, preparation and analysis were conducted using the Share-mind secure multi-party computation system that provided end-to-end cryptographic protection to the analysis. Using ten million tax records and half a million education records in the analysis, this is the largest cryptographically private statistical study ever conducted on real data.
Statistical Journal of the IAOS, 2019
We describe the use of secure multi-party computation for performing a large-scale privacy-preser... more We describe the use of secure multi-party computation for performing a large-scale privacy-preserving statistical study on real government data. In 2015, statisticians from the Estonian Center of Applied Research (CentAR) conducted a big data study to look for correlations between working during university studies and failing to graduate in time. The study was conducted by linking the database of individual tax payments from the Estonian Tax and Customs Board and the database of higher education events from the Ministry of Education and Research. Data collection, preparation and analysis were conducted using the Sharemind secure multi-party computation system that provided end-to-end cryptographic protection to the analysis. Using ten million tax records and half a million education records in the analysis, this is the largest cryptographically private statistical study ever conducted on
Big Data in Bioeconomy
Typically, data cannot be shared among competing organizations due to confidentiality or regulato... more Typically, data cannot be shared among competing organizations due to confidentiality or regulatory restrictions. We present several technological alternatives to solve the problem: secure multi-party computation (MPC), trusted execution environments (TEE) and multi-key fully homomorphic encryption (MKFHE). We compare these privacy-enhancing technologies from deployment and performance point of view and explain how we selected technology and machine learning methods. We introduce a demonstrator built in the DataBio project for securely combining private and public data for planning of fisheries. The secure machine learning of best catch locations is a web solution utilizing Intel® Software Guard Extensions (Intel® SGX)-based TEE and built with the Sharemind HI (Hardware Isolation) development tools. Knowing where to go fishing is a competitive advantage that a fishery is not interested to share with competitors. Therefore, joint intelligence from public and private sector data while...
Proceedings on Privacy Enhancing Technologies, 2016
We describe the use of secure multi-party computation for performing a large-scale privacy-preser... more We describe the use of secure multi-party computation for performing a large-scale privacy-preserving statistical study on real government data. In 2015, statisticians from the Estonian Center of Applied Research (CentAR) conducted a big data study to look for correlations between working during university studies and failing to graduate in time. The study was conducted by linking the database of individual tax payments from the Estonian Tax and Customs Board and the database of higher education events from the Ministry of Education and Research. Data collection, preparation and analysis were conducted using the Share-mind secure multi-party computation system that provided end-to-end cryptographic protection to the analysis. Using ten million tax records and half a million education records in the analysis, this is the largest cryptographically private statistical study ever conducted on real data.
Statistical Journal of the IAOS, 2019
We describe the use of secure multi-party computation for performing a large-scale privacy-preser... more We describe the use of secure multi-party computation for performing a large-scale privacy-preserving statistical study on real government data. In 2015, statisticians from the Estonian Center of Applied Research (CentAR) conducted a big data study to look for correlations between working during university studies and failing to graduate in time. The study was conducted by linking the database of individual tax payments from the Estonian Tax and Customs Board and the database of higher education events from the Ministry of Education and Research. Data collection, preparation and analysis were conducted using the Sharemind secure multi-party computation system that provided end-to-end cryptographic protection to the analysis. Using ten million tax records and half a million education records in the analysis, this is the largest cryptographically private statistical study ever conducted on
Big Data in Bioeconomy
Typically, data cannot be shared among competing organizations due to confidentiality or regulato... more Typically, data cannot be shared among competing organizations due to confidentiality or regulatory restrictions. We present several technological alternatives to solve the problem: secure multi-party computation (MPC), trusted execution environments (TEE) and multi-key fully homomorphic encryption (MKFHE). We compare these privacy-enhancing technologies from deployment and performance point of view and explain how we selected technology and machine learning methods. We introduce a demonstrator built in the DataBio project for securely combining private and public data for planning of fisheries. The secure machine learning of best catch locations is a web solution utilizing Intel® Software Guard Extensions (Intel® SGX)-based TEE and built with the Sharemind HI (Hardware Isolation) development tools. Knowing where to go fishing is a competitive advantage that a fishery is not interested to share with competitors. Therefore, joint intelligence from public and private sector data while...