AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

FedAdOb: Privacy-Preserving Fed erated Deep Learning With Ad aptive Ob fuscation

Hanlin Gu, Jiahuan Luo, Yan Kang, Yuan Yao, Gongxi Zhu, Bowen Li, Lixin Fan, Qiang Yang

TPAMI 2026 · Federated learning and privacy › Differential privacy · approach: Differentially private federated learning · 1 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
increase passport mean range N from 1 to 200 (ablation)FedAdOb · AlexNet-CIFAR10 VFL, CAFEfeature recovery error: 0.0589 -> 0.1205Improved
increase passport mean range N from 1 to 200 (ablation)FedAdOb · AlexNet-CIFAR10 VFL, CAFEmain task accuracy: 0.8798 -> 0.8739Hurt
increase passport variance sigma^2 from 0 to 100 (ablation)FedAdOb · AlexNet-CIFAR10 VFL, PMClabel recovery error: 0.368 -> 0.751Improved
increase passport variance sigma^2 from 0 to 100 (ablation)FedAdOb · AlexNet-CIFAR10 VFL, PMCmain task accuracy: 0.877 -> 0.791Hurt
use FedAdOb instead of no defenseVFL LeNet-MNIST · PMC attackCAP: 0.117 -> 0.506Improved
use FedAdOb instead of no defenseVFL LeNet-MNIST · CAFE attackCAP: 0.033 -> 0.137Improved
use FedAdOb instead of SplitFed against BMIHFL · MNIST BMIdata recovery error: 0.052 -> 0.071Improved
use FedAdOb instead of SplitFed against BGIHFL · MNIST BGIdata recovery error: 0.111 -> 0.111No clear effect
use FedAdOb instead of SplitFed against BGIHFL · CIFAR100 BGIdata recovery error: 0.087 -> 0.107Improved
use InstaHide defense in HFLFedAvg · CIFAR10 and CIFAR100main task accuracy: 18.6% and 10.66% best-case degradation, 52.12% and 16.65% worst caseHurt
use InstaHide instead of FedAdOb in VFL trainingVFL LeNet-MNIST · training time per epochtraining time (s): 7.05 -> 21.76Hurt
add FedAdOb to VFL trainingno-defense VFL · LeNet-MNISTtraining time per epoch (s): 7.03 -> 7.05No 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