AI Paper Atlas

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

FedIPR: Ownership Verification for Federated Deep Neural Network Models

Bowen Li, Lixin Fan, Hanlin Gu, Jie Li, Qiang Yang

TPAMI 2022 · Federated learning and privacy › Privacy attacks and secure learning · approach: Gradient inversion attacks · 116 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
add feature-based watermark embedding in FedAvg training (N=100 vs baseline)AlexNet on CIFAR10, 20 clients · CIFAR10 main accuracyaccuracy: 91.72% -> 90.62%Hurt
add feature-based watermark embedding (N=100) vs FedAvgResNet18 on CIFAR100, 20 clients · CIFAR100 main accuracyaccuracy: 76.52% -> 74.29%Hurt
add backdoor-based watermarks (N_T=50) vs FedAvgAlexNet on CIFAR10, 20 clients · CIFAR10 main accuracyaccuracy: 91.72% -> 91.69%No clear effect
embed watermarks in normalization layer scale parameters instead of convolution weights (ablation)FedIPR feature-based watermarks · fine-tuning attack, AlexNet CIFAR10feature detection rate eta_F: remains at 100% vs drops significantly for convolution layerImproved
embed watermarks in normalization layer rather than convolution layer (ablation)FedIPR feature-based watermarks · pruning attack, AlexNet CIFAR10feature detection rate eta_FImproved
increase total watermark bits KN beyond channel count M (ablation)FedIPR feature-based watermarks · feature detection rate vs bit lengthfeature detection rate eta_F: 100% -> about 80%Hurt
increase feature watermark length N per client from 50 to 500 (beta=0.1, non-iid) (ablation)ResNet on CIFAR100 · non-iid Dirichlet beta=0.1feature detection rate eta_F: 100.0% -> 78.45%Hurt
increase feature watermark length N per client from 50 to 300 (beta=0.1, non-iid) (ablation)AlexNet on CIFAR10 · non-iid Dirichlet beta=0.1feature detection rate eta_F: 100% -> 76.97%Hurt
increase backdoor trigger count per client from 50 to 300 (ablation)FedIPR backdoor watermarks, AlexNet CIFAR10 20 clients · CIFAR10 backdoor detectionbackdoor detection rate eta_T: 99.34% -> 98.85%No clear effect
replace FedAvg with Trim-mean defensive aggregation (ablation)FedIPR backdoor watermarks · CIFAR10 defensive aggregationbackdoor detection rate eta_T: 98.82% -> 63.25%Hurt
replace FedAvg with Bulyan defensive aggregation (ablation)FedIPR feature watermarks · CIFAR10 defensive aggregationfeature detection rate eta_F: 100% -> 98.75%No clear effect
lower client sampling ratio c to 0.25 (ablation)FedIPR · client selection, 10 clientsdetection rates eta_F and eta_TNo clear effect

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