Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning

arXiv:2403.18144v1 Announce Type: cross
Abstract: Federated learning is a decentralized learning paradigm introduced to preserve privacy of client data. Despite this, prior work has shown that an attacker at the server can still reconstruct the private training data using only the client updates. These attacks are known as data reconstruction attacks and fall into two major categories: gradient inversion (GI) and linear layer leakage attacks (LLL). However, despite demonstrating the effectiveness of these attacks in breaching privacy, prior work has …

abstract arxiv attacks client cs.cr cs.cv data decentralized federated learning leak leaked learn paradigm prior privacy server train training training data type updates work