Project Lead: Dr. Joshua Baron
Sponsoring Organization: DARPA
Project Synopsis: CSL aims to develop methods to protect data, models and model outputs among a community of entities who want to securely share their information to better inform machine learning (ML) model development. This effort will focus on creating working prototypes of computational techniques to improve ML models, and provide insights and methods that support privacy preservation and data security to assure that each entity’s individual, pre-existing datasets and models remain private. Possible technical approaches include drawing upon cryptographic methods (e.g., secure multiparty computation, homomorphic encryption, etc.), differential privacy and other methodologies.