AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

AEMIM: Adversarial Examples Meet Masked Image Modeling

Wenzhao Xiang, Chang Liu, Hang Su, Hongyang Yu

IJCV 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Biologically inspired robust vision · 2 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 adapters (norm layer) for adversarial/clean branches (ablation)AEMIM ViT-S/16 · ImageNet-1k val (ablation, 300 ep)top-1 accuracy: 81.2 -> 81.4Improved
use L2 distance as adversarial loss rather than reconstruction loss (ablation)AEMIM ViT-S/16 · ImageNet-1k val (ablation, 300 ep)top-1 accuracy: 81.1 -> 81.4Improved
use L2 distance rather than KLD as adversarial loss (ablation)AEMIM ViT-S/16 · ImageNet-1k val (ablation, 300 ep)top-1 accuracy: 81.3 -> 81.4Improved
use 2 attack steps rather than 1 (ablation)AEMIM ViT-S/16 · ImageNet-1k val (ablation, 300 ep)top-1 accuracy: 81.2 -> 81.4Improved
use 3 attack steps rather than 2 (ablation)AEMIM ViT-S/16 · ImageNet-1k val (ablation, 300 ep)top-1 accuracy: 81.4 -> 81.4No clear effect
perturbation budget eps=2 rather than eps=4 (ablation)AEMIM ViT-S/16 · ImageNet-1k val (ablation, 300 ep)top-1 accuracy: 81.2 -> 81.4Improved
perturbation budget eps=2 rather than eps=1 (ablation)AEMIM ViT-S/16 · ImageNet-1k val (ablation, 300 ep)top-1 accuracy: 81.3 -> 81.4Improved
add AEMIM auxiliary adversarial reconstruction to SimMIMSimMIM Swin-B 100 ep · ImageNet-1k valtop-1 accuracy: 83.5 -> 83.7Improved
add AEMIM to SimMIM on OOD variantsSimMIM Swin-B 100 ep · ImageNet-Aaccuracy: 34.9 -> 36.5Improved
add AEMIM to SimMIM on ImageNet-V2SimMIM Swin-B 100 ep · ImageNet-V2accuracy: 72.8 -> 72.7Hurt
add AEMIM to MAE pre-training (800 ep)MAE ViT-B/16 · ImageNet-1k valtop-1 accuracy: 83.3 -> 83.8Improved
add AEMIM to MAE under large FGSM budgetMAE ViT-B/16 800 ep · FGSM eps=8accuracy: 32.1 vs 33.0Hurt

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