LGAICRMay 15, 2025

Cutting Through Privacy: A Hyperplane-Based Data Reconstruction Attack in Federated Learning

arXiv:2505.10264v22 citationsh-index: 7UAI
Originality Highly original
AI Analysis

This work addresses a critical security issue for users of Federated Learning systems by exposing a severe privacy risk, representing a significant advancement over prior attacks.

The paper tackles the problem of data privacy vulnerabilities in Federated Learning by introducing a hyperplane-based attack that perfectly reconstructs clients' private training data from model updates, achieving perfect recovery of data batches two orders of magnitude larger than existing methods.

Federated Learning (FL) enables collaborative training of machine learning models across distributed clients without sharing raw data, ostensibly preserving data privacy. Nevertheless, recent studies have revealed critical vulnerabilities in FL, showing that a malicious central server can manipulate model updates to reconstruct clients' private training data. Existing data reconstruction attacks have important limitations: they often rely on assumptions about the clients' data distribution or their efficiency significantly degrades when batch sizes exceed just a few tens of samples. In this work, we introduce a novel data reconstruction attack that overcomes these limitations. Our method leverages a new geometric perspective on fully connected layers to craft malicious model parameters, enabling the perfect recovery of arbitrarily large data batches in classification tasks without any prior knowledge of clients' data. Through extensive experiments on both image and tabular datasets, we demonstrate that our attack outperforms existing methods and achieves perfect reconstruction of data batches two orders of magnitude larger than the state of the art.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes