Data Reconstruction Attacks and Defenses: A Systematic Evaluation

arXiv:2402.09478v1 Announce Type: cross
Abstract: Reconstruction attacks and defenses are essential in understanding the data leakage problem in machine learning. However, prior work has centered around empirical observations of gradient inversion attacks, lacks theoretical groundings, and was unable to disentangle the usefulness of defending methods versus the computational limitation of attacking methods. In this work, we propose a strong reconstruction attack in the setting of federated learning. The attack reconstructs intermediate features and nicely integrates with and outperforms most of …

abstract arxiv attacks computational cs.cr cs.lg data data leakage evaluation gradient machine machine learning prior type understanding work