AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

FLSeg: Enhancing Privacy and Robustness in Federated Learning under Heterogeneous Data via Model Segmentation

Zichun Su, Zhi Lu, Yutong Wu, Renfei Shen, Songfeng Lu

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 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
apply Krum on model segments (Segment Aggregation) instead of whole modelKrum · CIFAR-100 Min-Max 20%top-1 accuracy (%): 16.38 -> 46.05Improved
apply Krum on model segments instead of whole modelKrum · CIFAR-10 Min-Max 20%top-1 accuracy (%): 45.46 -> 60.82Improved
apply DnC on model segments instead of whole modelDnC · CIFAR-10 Min-Max 20%top-1 accuracy (%): 50.62 -> 64.59Improved
apply DnC on model segments instead of whole modelDnC · CIFAR-100 Min-Max 20%top-1 accuracy (%): 34.23 -> 51.11Improved
use DnC (SVD spectral) instead of Krum inside FLSegFLSeg · CIFAR-10 Min-Max 20%top-1 accuracy (%): 60.82 -> 64.59Improved
replace ACORN with FLSeg(DnC) under Min-Max attackersACORN · CIFAR-10 Min-Max 20%top-1 accuracy (%): 48.21 -> 64.59Improved
replace PEFL with FLSeg(DnC) under Min-Max attackersPEFL · FEMNIST Min-Max 20%top-1 accuracy (%): 21.32 -> 77.74Improved
replace ACORN with FLSeg(DnC) with no attackACORN · CIFAR-10 no attacktop-1 accuracy (%): 49.08 -> 63.99Improved
use Segment Exchange with PRNG seeds instead of SMPC (ACORN) for privacy, client sideACORN · n=1000, l=1e6client computation time (ms): 1696 ms -> 233 msImproved
use Segment Exchange instead of SMPC for server-side privacy costACORN · n=1000, l=1e6server time per client (ms): 181 ms -> 78 msImproved
choose segment size 10^4 instead of whole model (ablation)FLSeg(DnC) · CIFAR-10 Min-Maxtop-1 accuracy (%): 57.75% -> 65.72%Improved
reduce segment size from 10^4 to 10^2 (ablation)FLSeg(DnC) · CIFAR-10 Min-Maxtop-1 accuracy (%): 65.72% -> 63.93%Hurt

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