Privacy-preserving collaborative learning allows multiple data-owners to jointly train machine learning models while keeping their individual datasets private from each other. The main bottleneck against the scalability of such systems to a large number of participants is their communication cost. In this talk, we will introduce novel distributed training frameworks that can achieve scalability and privacy-protection simultaneously. The proposed frameworks provide strong information-theoretic privacy guarantees against (computationally) unbounded adversaries, while achieving significant reduction in the communication overhead against state-of-the-art secure training protocols.

Dr. Basak Guler