AI Paper Atlas

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

Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation

Guangnian Wan, Haitao Du, Xuejing Yuan, Jun Yang, Meiling Chen, Jie Xu

ICCV 2023 · Federated learning and privacy › Privacy attacks and secure learning · approach: Gradient inversion attacks · 2 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
perturb local learning rates uniformly at random (LRP) instead of fixed rates (ablation)FedAvg (ResNet-18) · CIFAR-10 (IID)test accuracy (%): 94.30 -> 94.15No clear effect
perturb local learning rates uniformly at random (LRP) (ablation)FedAvg (ResNet-18) · CIFAR-100 (non-IID)test accuracy (%): 65.69 -> 65.44No clear effect
perturb local learning rates uniformly at random (LRP) (ablation)FedAvg (ResNet-18) · CIFAR-100 (IID)test accuracy (%): 72.15 -> 72.65No clear effect
add personalized LR expectations by class count (ada-LRP) on top of LRP (ablation)LRP · CIFAR-10 (non-IID)test accuracy (%): 93.03 -> 93.32Improved
add personalized LR expectations (ada-LRP) on top of LRP (ablation)LRP · CIFAR-100 (non-IID)test accuracy (%): 65.44 -> 65.69Improved
give larger LR to client with better data (eta1=0.005, eta2=0.02) instead of the reverse (ablation)FedAvg on two non-IID MNIST clients (CNN) · MNIST non-IID 2 clientstest accuracy (%): 85.97 -> 94.21Improved
use random uniform local LRs with same expectations on two-client MNIST (ablation)FedAvg (CNN, MLP, logistic regression) · MNIST non-IID 2 clientstest accuracy (%): 92.10 -> 92.00No clear effect
use LRP defense instead of Soteria, noise, clipping, compression baselinesFL on ImageNet vs GGL attack · ImageNet vs GGL attackMSE-R: 0.0114 -> 0.3181Improved
use LRP defense vs Clipping+NoiseFL vs GGL attack · ImageNet vs GGL attackLPIPS (VGG): 0.6448 -> 0.6966Improved
add ada-LRP on ImageNet vs vanilla (top-1 vs top-5) (ablation)FedAvg (RexNet-130) · ImageNet (non-IID)top-1 accuracy (%): 61.52 -> 61.66; top-5 83.10 -> 83.04Mixed

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