AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature

Wenhan Wu, Zhili He, Huanghuang Liang, Yili Gong, Jiawei Jiang, Chuang Hu, Dazhao Cheng

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 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
add orthogonal gradient projection between forgetting and retention gradients (ablation)ReMisVFU · SVHNclean accuracy: 65.04 -> 67.56Improved
add orthogonal gradient projection between forgetting and retention gradients (ablation)ReMisVFU · SVHNbackdoor success rate (lower better): 11.65 -> 10.22Improved
add orthogonal gradient projection between forgetting and retention gradients (ablation)ReMisVFU · CIFAR-10clean accuracy: 57.54 -> 58.45Improved
add orthogonal gradient projection between forgetting and retention gradients (ablation)ReMisVFU · CIFAR-10backdoor success rate (lower better): 14.07 -> 10.55Improved
use orthogonal projection instead of a random unit vector of same norm (ablation)ReMisVFU · SVHNclean accuracy: 35.62 -> 67.56Improved
use orthogonal projection instead of a random unit vector of same norm (ablation)ReMisVFU · CIFAR-10backdoor success rate (lower better): 87.21 -> 10.55Improved
increase anchor scale c to 4 or more (ablation)ReMisVFU · SVHN and CIFAR-10forgetting (backdoor success)Hurt
increase anchor scale c up to 2 (from 0.5) (ablation)ReMisVFU · SVHN and CIFAR-10clean accuracy and backdoor successNo clear effect
increase retention weight alpha above 5x10^-3 (ablation)ReMisVFU · SVHN and CIFAR-10backdoor success rate: exceeds 50%Hurt
increase alpha from 1x10^-4 to 1x10^-3 (ablation)ReMisVFU · SVHN and CIFAR-10clean accuracyImproved
use ReMisVFU instead of FedGA gradient-ascent unlearningFedGA · five image benchmarksmembership inference AUC: 1.000 -> 0.576 (CIFAR-10)Improved
use ReMisVFU instead of full retrainingFedRetrain · five image benchmarksunlearning time: 10.63%-21.49% of FedRetrain timeImproved

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