Approximate and Weighted Data Reconstruction Attack in Federated Learning

arXiv:2308.06822v2 Announce Type: replace-cross
Abstract: Federated Learning (FL) is a distributed learning paradigm that enables multiple clients to collaborate on building a machine learning model without sharing their private data. Although FL is considered privacy-preserved by design, recent data reconstruction attacks demonstrate that an attacker can recover clients' training data based on the parameters shared in FL. However, most existing methods fail to attack the most widely used horizontal Federated Averaging (FedAvg) scenario, where clients share model parameters after multiple …

arxiv attack attacker attacks building can clients cs.ai cs.cr cs.lg data design distributed federated federated learning machine machine learning math.oc paradigm privacy private private data recover sharing training training data