Sarus Private Learning

Sarus solves the problem of data access when doing analytics and machine learning on confidential or personal information. With Sarus, data practitioners can seamlessly carry out analyses on any sensitive information without seeing the data. 

Sarus deploys inside the client's Azure cloud and acts as a gateway between the sensitive data and the analyst. By using the Sarus gateway, the analyst can query the remote data using standard SQL queries or machine learning libraries from their preferred environment (PowerBI, Metabase, python notebook). The gateway enforces differential privacy into each query before executing them on the original data. Differential privacy is the highest standard of privacy and guarantees that no personal information may leak out. 

(more details). 

Sarus targets Chief data officers, CTOs and Chief compliance officers that want to provide the best balance between efficiency and privacy.

The software is then used by the analysts, the data scientists, and the data engineers to carry out their data objectives in an efficient way.

Sarus addresses the following needs:

- Remove data friction: Using Sarus divides by 10 time-to-data for every new data project. 

- Data-centric orgs: with Sarus, a private access can be shared broadly across the organization, even for the most sensitive datasets 

- Break data Silos: working on data from different legal entities, geographic borders or even external partner no longer requires exposing confidential information, making those projects very easy to launch

- Data sharing: with Sarus, organizations can partner with external data sources or external data practitioners without personal information being exposed

- Scalable compliance: Sarus mathematical approach provides the highest guarantees in all use cases. Privacy policy templates can be scaled easily to all future use cases without bespoke validation processes

- Remove engineering bottlenecks (No code): Sarus removes the need for bespoke anonymization processes that are engineering heavy. Analysts work off the original data without compliance risk.

- Enhanced data security: with Sarus, no copy of the data is made and shared outside of the original location limiting the complexity of securing data assets. It also makes it much easier to fullfill data subject requests.