Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach

arXiv:2403.01268v1 Announce Type: new
Abstract: Federated Learning (FL) trains a black-box and high-dimensional model among different clients by exchanging parameters instead of direct data sharing, which mitigates the privacy leak incurred by machine learning. However, FL still suffers from membership inference attacks (MIA) or data reconstruction attacks (DRA). In particular, an attacker can extract the information from local datasets by constructing DRA, which cannot be effectively throttled by existing techniques, e.g., Differential Privacy (DP).
In this paper, we aim to …

abstract arxiv attacks box cs.cr cs.dc cs.lg data data sharing federated learning inference information leak machine machine learning parameters privacy theory trains type