Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attacks

arXiv:2403.03149v1 Announce Type: cross
Abstract: Recent studies have revealed that federated learning (FL), once considered secure due to clients not sharing their private data with the server, is vulnerable to attacks such as client-side training data distribution inference, where a malicious client can recreate the victim's data. While various countermeasures exist, they are not practical, often assuming server access to some training data or knowledge of label distribution before the attack.
In this work, we bridge the gap by proposing …

abstract arxiv attacks client cs.cr cs.dc cs.lg data distribution federated learning inference private data robust server studies training training data type vulnerable