Introducing OpaquePrompts, a privacy layer for LLMs. Click to learn more!

Community

MC2: An Open Source Project for Secure Analytics and Machine Learning

The MC2 (Multiparty Collaboration and Competition) is an open source Spark-based framework for running secure analytics and machine learning on encrypted data that was created out of research in the UC Berkeley RISE Lab. MC2 consists of an assortment of sub-components that enables several data owners to perform analytics and/or jointly train ML models on their collective data without revealing their individual data to each other. The open source community contributes to MC2 to advance secure analytics and AI for confidential computing.

MC2 on Github

The MC2 repository contains the source code for the MC2 client, which enables users to easily interface with MC2 services deployed remotely in the cloud. The MC2 stack supports a single client interface, as well as the following compute services:

Opaque SQL

Encrypted data analytics on Spark SQL using hardware enclaves

Secure XG Boost

Collaborative XGBoost training and inference on encrypted data using hardware enclaves

Federated XG Boost

Collaborative XGBoost in the federated setting

Join the Community

Join the discussion on Slack or email us at [email protected].

Join us for the Confidential Computing Summit 2023!

The Summit for All Things Confidential Computing

For the first time, a Summit that brings together the premier technology providers, researchers, as well as existing or potential users to help organizations advance confidential computing, and data clean rooms.

Register
Collaborate without compromise.

See Opaque in action. Request a demo to see Opaque’s secure multi-party analytics & AI and Data Clean Rooms for use cases across AdTech, Finance, Insurance, Healthcare and more.

Request a Demo