Encrypted Computation in Apache Spark

Download Slides

Homomorphic encryption is a relatively new type of encryption technology that allows computations to be done directly on encrypted data. ”Microsoft SEAL” is an easy-to-use homomorphic encryption library that enables software engineers to build end-to-end encrypted data storage and computation services where the customer never needs to share their key with the service. Bottlenecks in the technology are in performance and the size of encrypted data, and Spark, along with hardware acceleration, can help solve these scalability challenges. In this talk we will describe homomorphic encryption at a high level, and see what the performance of the technology can be when complex encrypted computations are executed in Spark. The talk will include demos.


Try Databricks
See More Spark + AI Summit Europe 2019 Videos

« back
Kim Laine
About Kim Laine


Kim Laine is a researcher in the Cryptography Research Group at Microsoft Research, Redmond WA. He holds a Master's degree in mathematical physics from University of Helsinki, Finland, and a PhD in mathematics from UC Berkeley. Currently Kim is working primarily on theory and practice of homomorphic encryption, and is leading the development of the homomorphic encryption library ''Microsoft SEAL''.