AI Paper Atlas

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

Scalable Privacy-Preserving Neural Network Training over Z2k via RMFE-Based Packing and Mixed-Circuit Computation

Hengcheng Zhou

AAAI 2026 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private 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
add mixed-circuit (bit-wise comparison) truncation instead of arithmetic-only truncationRMFE-packed Galois ring training · 13-bit truncation, rho=1, LAN onlineonline time (ms): 67.42 -> 17.83Improved
use PiTrun instead of PiEdabitsR (rho=1)truncation protocol · LAN truncationonline time: offline 0.63 -> 0.85 s slower; online 64.40 -> 17.83 msMixed
use the ours framework instead of Zhou 2025a (same packing density)end-to-end training Network B · Network B LAN, max pooling (2,3)training time (h): 12.19 -> 3.86Improved
use ours instead of Zhou 2025a on Network A in WANend-to-end training · Network A WAN, max pooling (1,3)WAN time (h): 36.74 -> 34.78Improved
switch max pooling to average pooling (ablation)Ours (2,3), Network B · Network B LANtraining time (h): 3.86 -> 1.88Improved
increase packed secrets rho from 1 to 2 (d=3) (ablation)Ours, Network B, max pooling · Network B LANtraining time (h): 7.84 -> 3.86Improved
use (3,5)-RMFE instead of (2,d)-RMFEs for 8<=n<=15 parties on Network A (ablation)Ours · Network A scalabilitytraining timeHurt
use (3,5)-RMFE instead of (2,d)-RMFEs for n>=16 parties (ablation)Ours · scalability, Networks A-Ctraining timeImproved
use (3,5)-RMFE instead of (2,d)-RMFEs on CNNs (ablation)Ours · Networks B and C scalabilitycommunicationImproved
raise fixed-point precision f from 13 to 20 (ablation)ciphertext training · Network A MNIST, 15 epochsaccuracy (%): 52.63 -> 91.78Improved
raise fixed-point precision from f=13 to f=16 (ablation)ciphertext training · Network A MNIST, 15 epochsaccuracy (%): 52.63 -> 80.11Improved

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