M7 P2PDL: Peer-to-Peer Deep Learning using Blockchain for Effective Domain Adaptation & Privacy Preserving

PI: Yugyung Lee

This project explores domain adaptation & online learning for model customization considering privacy preservation and secure communication. We propose blockchain-based peer-to-peer federated learning (P2PDL) using federated learning applications.


(1)Effective deep learning model sharing through peer-to-peer collaboration.

(2)Personalized or customized modeling for domain adaptation considering your own data

(3)Blockchain and privacy preservation for peer-to-peer deep learning.

(4)Noise modeling and Homomorphic encryption modeling