Label Inference Attacks against Node-level Vertical Federated GNNs

arXiv:2308.02465v2 Announce Type: replace
Abstract: Federated learning enables collaborative training of machine learning models by keeping the raw data of the involved workers private. Three of its main objectives are to improve the models' privacy, security, and scalability. Vertical Federated Learning (VFL) offers an efficient cross-silo setting where a few parties collaboratively train a model without sharing the same features. In such a scenario, classification labels are commonly considered sensitive information held exclusively by one (active) party, while other (passive) …

abstract arxiv attacks collaborative cs.cr cs.lg data federated learning gnns inference machine machine learning machine learning models node parties privacy raw scalability security training type workers