AI Paper Atlas

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

Fisher Calibration for Backdoor-Robust Heterogeneous Federated Learning

Wenke Huang, Mang Ye, zekun shi, Bo Du, Dacheng Tao

ECCV 2024 · Federated learning and privacy › Privacy attacks and secure learning · approach: Defending federated learning against poisoning · 8 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 Fisher Difference Regularization and Fisher Discrepancy Aggregation together (ablation)FedAvg under backdoor attack · Cifar-10 (beta=0.5, 30% malicious)trade-off V: 48.84 -> 75.39Improved
add Fisher Difference Regularization alone (ablation)SDFC · MNIST (beta=0.5, 30% malicious)trade-off V: 49.93 -> 92.96Improved
add Fisher Discrepancy Aggregation alone (ablation)SDFC · MNIST (beta=0.5, 30% malicious)trade-off V: 49.93 -> 50.34No clear effect
add FDAgg on top of FDReg (ablation)SDFC · Cifar-10 (beta=0.5, 30% malicious)trade-off V: 64.42 -> 75.39Improved
use absolute difference of local and validation Fisher instead of either alone (ablation)FDReg · Cifar-10 (beta=0.5, 30% malicious)trade-off V: 58.45 / 48.33 -> 75.39Improved
use Fisher (squared gradient) importance instead of absolute gradient (ablation)FDReg · Cifar-10 (beta=0.5, 30% malicious)trade-off V: 58.36 -> 64.42Improved
increase regularization strength lambda (ablation)FDReg · MNIST (beta=0.5, 30%/50% malicious)trade-off V: 78.96/81.79 at lambda=1 -> 93.45/92.97 at larger lambdaImproved
reduce clean validation set from 256 to 16 samples (ablation)SDFC · Cifar-10 (beta=0.5, 30% malicious)trade-off V: 75.39 -> 75.60No clear effect
increase local epochs from 10 to 40 (ablation)SDFC · MNIST (beta=0.5, 30% malicious)trade-off V: 93.48 -> 89.14Hurt
use SDFC instead of strongest client-wise defenses at 50% malicious clientsbackdoor-robust FL · MNIST (beta=0.5, 50% malicious)trade-off V: 50.43 -> 76.85Improved
use SDFC instead of DnCbackdoor-robust FL · MNIST/Cifar-10 (beta=0.5, 30% malicious)trade-off V: DnC 94.16 vs SDFC 92.98 (MNIST); 75.58 vs 75.39 (Cifar-10)No 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