AI Paper Atlas

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

AdaEA++: Enhanced Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability

Bin Chen, Jia-Li Yin, Bo‐Hao Chen, Ximeng Liu, Yuanlong Yu

IJCV 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples · 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
add adaptive gradient modulation (AGM) (ablation)naive ensemble attack · CIFAR-10average ASR: 27.29 -> 39.79 (+12.5)Improved
add disparity-reduced filter (DRF) (ablation)naive ensemble attack · CIFAR-10average ASR: 27.29 -> 42.42 (+15.13)Improved
add DRF (ablation)naive ensemble attack · CIFAR-10 (ViT targets)average ASR: 23.94 -> 47.57Improved
combine AGM and DRF (ablation)naive ensemble attack · CIFAR-10average ASR: 27.29 -> 44.78 (+22.4)Improved
increase weighting scale beta in AGM (ablation)AdaEA · CIFAR-10 (Res-18, ViT-T)average ASRMixed
increase binarization threshold eta in DRF (ablation)AdaEA · CIFAR-10 (Res-18, ViT-T)average ASRMixed
replace Ens with AdaEA on I-FGSMensemble attack · CIFAR-10average ASR: 26.56 -> 45.09Improved
replace Ens with AdaEA on I-FGSMensemble attack · ImageNetaverage ASR: 46.38 -> 49.36Improved
use SVRE instead of Ens with MI-FGSMensemble attack · CIFAR-10average ASR: 37.07 -> 23.04Hurt
use SVRE instead of Ens with DI2-FGSMensemble attack · CIFAR-10average ASR: 72.44 -> 33.49Hurt
replace Ens with AdaEA on DI2-FGSMensemble attack · CIFAR-10average ASR: 72.44 -> 80.32Improved
use four surrogate models instead of two (ablation)AdaEA · CIFAR-10average ASRImproved

Later papers that compared with this method

1 later accepted paper reports AdaEA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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