CrossPriv
Finalist for ACM Student Research Competition at 35th IEEE/ACM Conference for ASE.
Advised By: Peer Led
The design and implementation of artificial intelligence driven software that keeps user data private is a complex yet necessary requirement in the current times. Developers must consider several ethical and legal challenges while developing services which relay massive amount of private information over a network grid which is susceptible to attack from malicious agents. In most cases, organizations adopt a traditional model training approach where publicly available data, or data specifically collated for the task is used to train the model. Specifically in the healthcare section, the operation of deep learning algorithms on limited local data may introduce asignificant bias to the system and the accuracy of the model maynot be representative due to lack of richly covariate training data.In this paper, we propose CrossPriv,a user privacy preservation model for cross-silo Federated Learning systems to dictate some preliminary norms of SaaS based collaborative software. We discuss the client and server side characteristics of the software deployedon each side. Further, We demonstrate the efficacy of the proposed model by training a convolution neural network on distributed dataof two different silos to detect pneumonia using X-Rays whilst notsharing any raw data between the silos.
Resources