AI Paper Atlas

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

Retaliatory Attacks Against Federated Unlearning via Data Leakage

Xinyi Sheng, Wei Bao, Hequn Wang, Yuqin Liu, Sen Fu

AAAI 2026 · Federated learning and privacy › Privacy attacks and secure learning · approach: Defending federated learning against poisoning · 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
launch AUA (relearn reconstructed unlearned data)Retrain/FedEraser/KD/SGA/RobustFU · Location, Purchase100MIA accuracy and unlearned accuracy: MIA 0.502 -> 0.629; UA 0.606 -> 0.950 (Location, Retrain)Improved
launch DUA (negative gradient on reconstructed data)all FU methods · Location, Purchase100unlearned accuracy (UA): 0.606 -> 0.544 (Location, Retrain); 0.578 -> 0.497 (Purchase100)Improved
DUA effect on normal test accuracyall FU methods · Location, Purchase100test accuracy (TA): 0.611 -> 0.598; 0.637 -> 0.619 (Retrain)Hurt
unlearning-induced MIA across image datasetsFU methods · CIFAR-10, SVHNU-MIA accuracy: 0.654 (CIFAR-10, Retrain); 0.693 (SVHN, Retrain)Improved
full coarse-to-fine pipeline vs single attack-model prediction, coarse-only or no filtering variants (S1-S3) (ablation)AUA/DUA reconstruction · Location, Purchase100 (Retrain)MIA increase / UA decreaseImproved
unlearning-induced MIA data reconstruction vs baselines B1-B3AUA/DUA · Location, Purchase100 (Retrain)MIA increase / UA decreaseImproved

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