AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling

Georgi Ganev, MohammadReza Nazari, Rees Davison, Amirhassan Fallah Dizche, XINMIN WU, Ralph Abbey, Jorge G Silva, Emiliano De Cristofaro

ICLR 2026 · Federated learning and privacy › Differential privacy · approach: Differentially private synthetic data · 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
use naive distinguishing/DCR-style linkability to assess SMOTE privacySMOTE augmented/synthetic data · 8 imbalanced datasetsattack success: naive 0.01 precision vs DistinSMOTE 1.00Hurt
apply SMOTE augmentation before training classifiers (vs real data only) (ablation)MIA target vulnerability · 8 imbalanced datasetsMIA AUC: 0.58 -> 0.68 (17% rise)Hurt
higher imbalance ratio r (ablation)ReconSMOTE · 8 imbalanced datasets, synthetic datarecall: 0.43 (r=8.6) -> 1.00 (r>=26)Improved
reduce SMOTE neighbors from k=5 to k=2 (ablation)ReconSMOTE · 8 imbalanced datasetsrecall: 0.85 -> 0.52Hurt
reduce SMOTE neighbors from k=5 to k=2 (ablation)DistinSMOTE · 8 imbalanced datasetsprecision/recall: 1.00 -> 1.00No clear effect
use SMOTE-NC with mixed-type data, ignoring categorical features (ablation)ReconSMOTE · cardio, churnrecall: 1.00 -> 0.98No clear effect
add small noise (<=1e-7) to SMOTE interpolation (ablation)DistinSMOTE/ReconSMOTE · yeast_me2precision: 1.00 -> 0.96 (Recon, 1e-7)No clear effect
add large noise (1e-3) to SMOTE interpolation (ablation)ReconSMOTE · yeast_me2precision/recall: 1.00 -> 0.00Hurt
match attack tolerance to injected noise level (ablation)DistinSMOTE/ReconSMOTE · yeast_me2precision: 0.07 vs 0.04 at noise 1e-5 (Distin)Improved

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