AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Semi-Leak: Membership Inference Attacks against Semi-Supervised Learning

Xinlei He, Hongbin Liu, Neil Zhenqiang Gong, Yang Zhang

ECCV 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Safe and realistic semi-supervised learning · 16 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
use A_DA instead of the best baseline attack A_NNmembership inference on FixMatch · CIFAR10 (500 labels)attack AUC: 0.722 -> 0.780Improved
increase augmented views from 10 to 100 (ablation)A_DA · CIFAR10 (FixMatch, 500 labels)attack AUC: 0.780 -> 0.806Improved
use JS Distance instead of cosine, correlation or Euclidean distance (ablation)A_DA · CIFAR10 (FixMatch, 500 labels)attack AUC: 0.679, 0.682, 0.749 -> 0.780Improved
enlarge target model from WRN28-1 to WRN28-8 (ablation)A_DA against FixMatch · CIFAR100 (500 labels)attack AUC: 0.726 -> 0.927Improved
raise unlabeled batch ratio from 1 to 16 (ablation)A_DA against FixMatch · CIFAR100 (500 labels)attack AUC: 0.578 -> 0.909Improved
raise unlabeled batch ratio from 1 to 16 (ablation)FixMatch target model · CIFAR100 (500 labels)test accuracy: 0.210 -> 0.247Mixed
use the strongest augmentation level 4 instead of level 0 (ablation)A_DA · CIFAR100 (FixMatch, 500 labels)attack AUC: 0.876 -> 0.882Improved
use ResNet50 shadow model instead of same-architecture WRN28-2 (ablation)A_DA · CIFAR100 (FixMatch, 500 labels)attack AUC: 0.880 -> 0.859Hurt
add early stoppingFixMatch target model · CIFAR100 (4,000 labels)attack AUC: 0.918 -> 0.695Improved
add early stoppingFixMatch target model · CIFAR100 (4,000 labels)test accuracy: 0.530 -> 0.490Hurt
add DP-SGDFixMatch target model · CIFAR100 (4,000 labels)test accuracy: 0.530 -> 0.034Hurt
add top-k (k=1) posterior releaseFixMatch target model · CIFAR100 (4,000 labels)attack AUC: 0.918 -> 0.906No 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