Confidential Computing for Machine Learning

Sadegh Riazi on building tools for privacy-preserving machine learning and analytics based on secure multi-party computation.

SubscribeApple • Android • Spotify • Stitcher • Google • AntennaPod • RSS.

Sadegh Riazi is CEO and co-founder of CipherMode Labs1, a startup building tools that enable data and machine learning teams to build and deploy models directly on encrypted data. CipherMode’s new open source project enables teams to develop and deploy machine learning algorithms using familiar tools, and thus opens up the possibility of using sensitive data in different scenarios both within an organization, and in cooperation with other organizations.

Subscribe to the Gradient Flow Newsletter.

An effective data privacy and security policy will protect data in three states: at rest, in use, and in transit. While there  have been other tools that allow teams to build and deploy models against encrypted data, in the past such tools have been too slow to be of practical use (even model inference was too slow).  CipherMode is the first practical tool for building ML models against sensitive data.

Figure: CipherCore includes an intermediate representation layer of computation graphs between the application layer and the protocol layer.

Highlights in the video version:

Related content:

FREE report:

[1] Ben Lorica is an investor in CipherMode Labs.

[Image: Blocks outside The Source in Sioux Falls by Ben Lorica.]