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

arXiv:2403.01268v1 Announce Type: cross
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 …

arxiv attacks box clients cs.cr cs.dc cs.lg data data sharing defending dra federated federated learning high information leak machine machine learning privacy sharing theory trains