AI Paper Atlas

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

Boosting the Transferability of Adversarial Samples via Attention

Weibin Wu, Yuxin Su, Xixian Chen, Shenglin Zhao, Irwin King, Michael R. Lyu, Yu-Wing Tai

CVPR 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples · 157 citations (OpenAlex)

Check 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 attention-guided feature destruction to BIMInception V3 source attack · ImageNet-compatible, Inception V3 targettop-1 accuracy: 0.01% -> 0.1%No clear effect
Add attention-guided feature destruction to BIMInception V3 source attack · ImageNet-compatible, Inception V4 targettop-1 accuracy: 67.7% -> 22.1%Improved
Add attention-guided feature destruction to BIMInception V3 source attack · ImageNet-compatible, Inception-ResNet V2 targettop-1 accuracy: 70.2% -> 25.7%Improved
Add attention-guided feature destruction to BIMInception V3 source attack · ImageNet-compatible, ensemble targettop-1 accuracy: 73.6% -> 31.9%Improved
Add attention-guided feature destruction to BIMInception V3 source attack · ImageNet-compatible, Adv-Inc-v3 targettop-1 accuracy: 82.4% -> 54.1%Improved
Add attention-guided feature destruction to BIMInception V3 source attack · ImageNet-compatible, Adv-IncRes-v2 targettop-1 accuracy: 93.9% -> 61.3%Improved
Add attention-guided feature destruction to BIMInception V3 source attack · ImageNet-compatible, Ens3-Adv-Inc-v3 targettop-1 accuracy: 88.2% -> 60.2%Improved
Add attention-guided feature destruction to BIMInception V3 source attack · ImageNet-compatible, Ens4-Adv-Inc-v3 targettop-1 accuracy: 88.5% -> 60.2%Improved
Combine ATA with TAP (ablation)Inception V4 source attack · ImageNet-compatible black-box targetsattack success rate: 6.8%Improved
Combine ATA with TI (ablation)Inception V4 source attack · ImageNet-compatible black-box targetsattack success rate: 4.6%Improved

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