CryptoNumerics enables Privacy-Protected Data Science by using a combination of Decentralized Differential Privacy, Decentralized Private Set Intersection and Decentralized Private Statistical and Machine Learning Model Building.

Decentralized Differential Privacy

Make data Differentially Private by applying random sampling, followed by optimal attribute generalization with configurable metrics of information loss. Protect PII in either a single dataset or across decentralized data aligned by CN-Insight when augmenting either features or observations.

Decentralized Private Set Intersection

Privately identify the intersection or symmetric difference of elements across sensitive datasets without revealing anything else and without using a “trusted” third party. Align datasets for use in decentralized private statistical and machine learning model building when augmenting either features or observations.

Decentralized Private Statistical and Machine Learning Model Building

Build private statistical and machine learning models across decentralized datasets without exposing or moving the data by using techniques from Secure Multiparty Computation. Retain control over the types and frequency of models trained on your data.