AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Boosting Adversarial Transferability via Ensemble Non-Attention

Yipeng Zou, Qin Liu, Jie Wu, Yu Peng, Guo Chen, Hui Zhou, Guanghui Ye

AAAI 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples · 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 non-attention meta-testing step to meta-gradient optimization (ablation)NAMEA · ImageNet, avg ASR over 9 ViTs and 8 CNNsaverage ASR: drop of 9.2% when removedImproved
add attention meta-training step (ablation)NAMEA · ImageNet, avg ASR over 9 ViTs and 8 CNNsaverage ASR: drop of 7.4% when removedImproved
add gradient scaling optimization (GSO) module (ablation)NAMEA · ImageNet, avg ASR over 9 ViTs and 8 CNNsaverage ASR: drop of 2% when removedImproved
fill masked attention areas with random noise instead of 0s or 1s (ablation)NAMEA NAE module · ImageNet, I-FGSMaverage ASR: about +2.7%Improved
set attention threshold eta to 0.6 rather than smaller or larger values (ablation)NAMEA · ImageNet, I-FGSM and MI-FGSMaverage ASRImproved
extract non-attention areas instead of attention areas or random patches for meta-testing (ablation)NAMEA · ImageNetaverage ASRImproved
choose meta-testing model by different-architecture, same-architecture or random strategy (ablation)NAMEA · ImageNetaverage ASRNo clear effect
replace NAE module with BSR random input transformation in meta-testing (ablation)NAMEA · ImageNetaverage ASRHurt
combine BSR input transformation with NAMEA under DI-MI-FGSMNAMEA · ImageNet, DI-MI-FGSMaverage ASRHurt
use NAMEA instead of SMER as ensemble attackDI-MI-FGSM · ImageNet, 17 target modelsaverage ASR: 78.5 -> 83.7 (CNNs); 72.1 -> 77.5 (ViTs)Improved
use NAMEA instead of SMER against DiffPure defenseDI-MI-FGSM · ImageNet, DiffPureattack success rate: 39.9 -> 50.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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