AI Paper Atlas

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

ULD-Net: Enabling Ultra-Low-Degree Fully Polynomial Networks for Homomorphically Encrypted Inference

Xi Xie, Ran Ran, Jiahui Zhao, Bin Lei, Zhijie Jerry Shi, Wujie Wen, Caiwen Ding

ICLR 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 ULD-Net quadratic activations with PolyNorm instead of cascaded polynomials (SMART-PAF)fully polynomial ResNet-18 · ImageNettop-1 accuracy: 69.40% -> 69.79%Improved
use degree-2 ULD-Net instead of SMART-PAF degree 81 for HE model latencyfully polynomial ResNet-18 · ImageNetmodel HE latency (s): 114277 -> 41408Improved
use degree-2 ULD-Net instead of SMART-PAF degree 81 for activation latencyfully polynomial ResNet-18 · ImageNetactivation latency (s): 8311 -> 1024Improved
use fully polynomial ULD-Net instead of partial replacement AutoRePResNet-18 · CIFAR-100top-1 accuracy: 75.48% -> 78.81%Improved
use fully polynomial ULD-Net instead of SNLResNet-18 · CIFAR-100model HE latency (s): 2052 -> 647Improved
use ULD-Net instead of NEXUS (low-degree RoPE, PolyNorm, PolyAct)ViT-Small · CIFAR-10non-polynomial operator latency (s): 7995 -> 390Improved
use ULD-Net instead of NEXUSViT-Small · Tiny-ImageNettop-1 accuracy: 60.52% -> 61.40%Improved
use ULD-Net instead of NEXUSViT-Small · CIFAR-10top-1 accuracy: 91.39% -> 91.48%Improved
increase PolyAct degree from 2 to 3 (ablation)ULD-Net VanillaNet-6 · ImageNettop-1 accuracy: 74.25% -> 76.03%Improved
increase PolyAct degree from 2 to 3 (ablation)ULD-Net VanillaNet-7 · ImageNettop-1 accuracy: 74.91% -> 76.40%Improved
increase PolyAct degree from 2 to 3 (ablation)ULD-Net VanillaNet-7 · ImageNetmodel HE latency (s): 5204 -> 5614Hurt
choose normalization axis per sample (all axes except batch) rather than over the batch (ablation)fully polynomial models · stability analysisnumerical stabilityImproved

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