AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

Protection against Source Inference Attacks in Federated Learning

Andreas Athanasiou, Kangsoo Jung, Catuscia Palamidessi

ICLR 2026 · Federated learning and privacy › Privacy attacks and secure learning · approach: Defending federated learning against poisoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
shuffle at parameter level instead of model levelshuffling defenses · SIA on CIFAR-10SIA accuracy: 50% to 28% (alpha=0.1)Improved
shuffle at layer level instead of parameter levelreconstruction attack · SIA on CIFAR-100 ResNet-18SIA accuracy: 78% vs 60% at alpha=0.1Hurt
add encoding on top of parameter-level shufflingparameter-level shuffling · SIA accuracy at all alphaSIA accuracy: reduces to random guess levelImproved
apply shuffling with encoding against data reconstruction attackCIFAR-10 DRA, 10 clients · CIFAR-10reconstruction loss: 3e-4 -> 0.98Improved
increase digit precision r for encoded fractional part (ablation)encoding algorithm · CIFAR-10 and CIFAR-100joint model accuracy: r=3 approaches vanilla FL; r=8 matches itImproved
increase digit precision r from 2 to 3 on MNIST (ablation)encoding algorithm · MNISTjoint model accuracyNo clear effect
use r=5 instead of vanilla 32-bit full values (ablation)encoding algorithm · CIFAR-100 ResNet (10 clients)top-1 accuracy: 55 -> 53No clear effect
add RLE compression under fully trusted shuffler (ablation)encoding algorithm · CIFAR-100 ResNet (10 clients)communication expansion: 1.81x -> 1.03xImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy