AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Fully Decentralized Certified Unlearning

Hithem Lamri, Michail Maniatakos

CVPR 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
route to the unlearning client with p=1.0 instead of p=0.1 (continuous unlearning) (ablation)RR-DU · MNISTtest accuracy (%): 99.18 -> 10.10Hurt
route to the unlearning client with p=1.0 instead of p=0.1 (continuous unlearning) (ablation)RR-DU · CIFAR-10test accuracy (%): 88.30 -> 17.74Hurt
route to the unlearning client with p=1.0 instead of p=0.1 (ablation)RR-DU · MNISTbackdoor accuracy (%): 10.33 -> 0.00Improved
use p=0.1 targeted unlearning instead of p=0 finetuning (ablation)RR-DU · CIFAR-10backdoor accuracy (%): 10.93 -> 11.20No clear effect
use p=0.1 targeted unlearning instead of p=0 finetuning (ablation)RR-DU · MNISTtest accuracy (%): 99.18 -> 99.18No clear effect
use RR-DU instead of finetuning after removing poisoned dataRR-DU · MNISTbackdoor accuracy (%): 18 -> 10Improved
use RR-DU instead of decentralized DP (DDP)RR-DU · MNISTbackdoor accuracy (%): 35 -> 10Improved
use RR-DU instead of DP-SGDRR-DU · MNISTbackdoor accuracy (%): 60 -> 10Improved
use RR-DU instead of DDPRR-DU · MNISTclean test accuracy (%): 96.7 -> 99.1-99.2Improved
use RR-DU instead of DP-SGD and DDPRR-DU · CIFAR-10clean test accuracy (%): 50-55 -> 88-89Improved
use RR-DU instead of finetuningRR-DU · CIFAR-10backdoor accuracy (%): 25-30 -> 10Improved

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