New software processes and analyze encrypted data from multiple sources

Software that orchestrates secure and compliant data collaborations.


Follow us onFollow Tech Explorist on Google News

Businesses with quality data are more likely to collect actionable customer insights and more. However, the amount of data collected by companies and organizations is limited by regulations and practical constraints.

Gathering more data from more sources is better for analyses, modeling, and forecasting. That’s the reason businesses and organizations are increasingly entering into bilateral data-sharing agreements. But, there is also the concern of data theft and confidentiality.

The EPFL Center for Digital Trust spin-off Tune Insight has developed a new software program to support wider and more extensive data collaborations. The software is entirely scalable, can be deployed remotely, has been successfully trialed on various types of data, including medical records – arguably the most sensitive kind of information.

Dr. Juan Troncoso-Pastoriza, CEO of Tune Insight, said, “What’s more, our system keeps organizations compliant with strict data protection laws and regulations such as the GDPR, which governs data processing in the European Union and for European citizens.”

“We are entering a new era of data protection, with the ability to also encrypt data in use, in addition to encrypting data at rest and in transit. Tune Insight is at the forefront of this major transition.”

The system digs the data for information, yet the communications and calculations remain encrypted consistently. The technology is based on the principle of multiparty homomorphic encryption: an encryption algorithm hides specific numerical values in the data without compromising the ability to process it as usual.

Troncoso-Pastoriza said, “Our technology captures the same insights from encrypted data as a conventional system processing unencrypted information.”

The software allows users to statistically analyze data and develop artificial intelligence models collaboratively without sharing the underlying data sets. It also opens up new avenues for collaboration: by providing enhanced security guarantees, the system will make negotiating multilateral data transfer and processing agreements much more straightforward.

Troncoso-Pastoriza said“Existing technologies fall short of the mark when it comes to data protection. They require organizations to share intermediate results or add noise to the data. In other words, they partially protect information against leaks by sacrificing accuracy.”

Their findings were published in Nature Communications in October.

Journal Reference:

  1. David Froelicher et al. Truly privacy-preserving federated analytics for precision medicine with multiparty homomorphic encryption. DOI: 10.1038/s41467-021-25972-y