AI Paper Atlas

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

$\texttt{FHAIM}$: Fully Homomorphic AIM for Private Tabular Synthetic Data Generation

Mayank Kumar, Qian Lou, Paulo L. Barreto, Martine De Cock, Sikha Pentyala

ICML 2026 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning

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 exact squared L2 norm instead of polynomial-approximated L1 norm (ablation)FHAIM · breast-cancer, COMPAS, diabetes (eps = infinity)workload error / classification accuracyImproved
use exact squared L2 norm instead of polynomial-approximated L1 norm (ablation)FHAIM · eps = 1 (high privacy)classification accuracyImproved
switch from L1 to L2 norm in SELECT step (ablation)FHAIM · Cancerruntime per iteration: about 15% increaseHurt
switch from L1 to L2 norm (ablation)FHAIM · COMPASpeak memory (MB): 11.12 -> 31.72Hurt
run FHAIM encrypted instead of plaintext AIM-L1AIM · Adultgeneration time: 19 minutes -> 5.5 hoursHurt
run FHAIM encrypted instead of plaintext AIM-L2AIM · Adultgeneration time: 5 minutes -> 5.3 hoursHurt
add encryption of the data via FHE (FHAIM-L2 vs AIM-L2)AIM · three datasetsutilityNo 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