AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Partitioning for Intrinsic Model Inversion Resistance in Collaborative Inference

Rongke Liu, Youwen Zhu, Lei Zhou, Zhang Xianglong, Dong Wang

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Prototype and concept dictionary models · 0 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
partition at decision-level block 49+ instead of earlier blocksIR-152 · CIFAR-10 MIAreconstruction MSE: below 0.02 up to block 48, then sharp riseImproved
partition at VGG19 Block 39 instead of Block 30VGG19 · CIFAR-10 MIAreconstruction MSE: 0.066493 -> 0.136896Improved
increase depth of ViT partition pointViT (6-depth) · CIFAR-10 MIAreconstruction MSENo clear effect
train with label smoothing (ablation)IR-152 / VGG19 / ViT · CIFAR-10test accuracy: 90.59% -> 90.76% (IR-152)No clear effect
enrich Z with dropout NN module (concat) (ablation)IR-152 Block 50 · CIFAR-10 MIA, test setreconstruction MSE: 0.057010 -> 0.051740Hurt
enrich Z with FFT (residual) (ablation)IR-152 Block 50 · CIFAR-10 MIA, test setreconstruction MSE: 0.057010 -> 0.112854Improved
enrich Z with NN module without dropout (ablation)IR-152 Block 50 · CIFAR-10 MIAattack generalizationHurt
enrich Z with augmentation (ablation)IR-152 · CIFAR-10 MIAPSNR gain: +0.4 at Block 50 vs about +1.13 at Block 40Mixed
use attention-enhanced inversion model (ablation)IR-152 Block 50 · CIFAR-10 MIA, test setreconstruction MSE: 0.057010 -> 0.050579 (AttentionAsConv+SE+LSK+MSCA)Hurt
use auxiliary data from the same distribution as target (ablation)VGG19 · KMNIST reconstructionreconstruction qualityImproved
use dimension normalization in R2c-based GPZ location (ablation)R2c locator · VGG19transition location: 26->30 and 39->43 vs 26->30 and 30->39Improved
use label smoothing for GPZ location (ablation)R2c locator · IR-152 / VGG19transition zoneNo 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