<ul><li>A new data reconstruction attack called Hyperplane-Based Data Reconstruction Attack has been introduced in Federated Learning (FL).</li><li>This attack overcomes limitations of existing data reconstruction attacks by leveraging a geometric perspective on fully connected layers.</li><li>The method enables the perfect recovery of arbitrarily large data batches in classification tasks without prior knowledge of clients' data.</li><li>Experiments on image and tabular datasets show that this attack outperforms existing methods and achieves perfect reconstruction of data batches two orders of magnitude larger than the state of the art.</li></ul>

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

Discover more