AI Paper Atlas

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

ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers

Hanwen Cao, Haobo Lu, Xiaosen Wang, Kun He

ICCV 2025 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on vision transformers · 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 model augmentation (MHD, ASS, MFM) to the ensemble (ablation)Ens baseline · Average ASR on ViT targetsattack success rate (%): 70.5 -> 93.4Improved
add model augmentation (MHD, ASS, MFM) to the ensemble (ablation)Ens baseline · Average ASR on CNN targetsattack success rate (%): 48.1 -> 78.8Improved
add automatic reweighting (ablation)Ens baseline · Average ASR on ViT targetsattack success rate (%): 70.5 -> 78.6Improved
add automatic reweighting (ablation)Ens baseline · Average ASR on CNN targetsattack success rate (%): 48.1 -> 52.6Improved
add step size enlargement (ablation)Ens baseline · Average ASR on ViT targetsattack success rate (%): 70.5 -> 87.1Improved
add step size enlargement (ablation)Ens baseline · Average ASR on CNN targetsattack success rate (%): 48.1 -> 65.5Improved
add automatic reweighting on top of augmentation and enlargement (ablation)ViT-EnsembleAttack · Average ASR on ViT targetsattack success rate (%): 98.0 -> 98.4Improved
add automatic reweighting on top of augmentation and enlargement (ablation)ViT-EnsembleAttack · Average ASR on CNN targetsattack success rate (%): 88.1 -> 88.3Improved
add automatic reweighting on top of augmentation (ablation)ViT-EnsembleAttack · Average ASR on ViT targetsattack success rate (%): 93.4 -> 95.7Improved
add step size enlargement on top of augmentation (ablation)ViT-EnsembleAttack · Average ASR on CNN targetsattack success rate (%): 78.8 -> 88.1Improved
increase step size factor q beyond 3 (to 5 and 10) (ablation)ViT-EnsembleAttack · Average ASR on ViTs and CNNsattack success rate (%)Hurt
increase inference loop count beyond 2 (ablation)ViT-EnsembleAttack · Average ASR on ViTs and CNNsattack success rate (%)No 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