AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-Directional Metric Learning

Hong Wang, Yuefan Deng, Shinjae Yoo, Haibin Ling, Yuewei Lin

ICCV 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training with feature consistency · 22 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 bidirectional metric learning in place of single-directional metric learning (ablation)AGKD-BML · CIFAR-10PGD-20 accuracy: 51.59% -> 60.51%Improved
add attention guided knowledge distillation alone to the adversarial training baseline (ablation)adversarial training · CIFAR-10PGD-20 accuracy: 45.57% -> 65.93%Improved
add AGKD to BML (ablation)BML · CIFAR-10PGD-20 accuracy: 60.51% -> 71.02%Improved
add BML to AGKD (ablation)AGKD · CIFAR-10PGD-20 accuracy: 65.93% -> 71.02%Improved
add BML to AGKD (ablation)AGKD · CIFAR-10CW-20 accuracy: 60.71% -> 63.67%Improved
add BML to AGKD (ablation)AGKD · CIFAR-10FGSM accuracy: 75.57% -> 76.69%Improved
train with 7-step attack instead of 2-stepAGKD-BML · CIFAR-10AutoAttack accuracy: 37.07% -> 50.59%Improved
train with 7-step attack instead of 2-stepAGKD-BML · CIFAR-10PGD-20 accuracy: 71.02% -> 57.30%Hurt
use class-irrelevant attention (AGKD) instead of class-relevant Grad-CAM attention of original class (ablation)AGKD · CIFAR-10PGD-20 accuracy: 59.06% -> 65.93%Improved
use CAM-avg class-irrelevant attention instead of AGKD attention (ablation)AGKD · CIFAR-10PGD-20 accuracy: 65.93% -> 66.55%No clear effect
train FS with a 2-step attack to match AGKD-BML training timefeature scattering · CIFAR-10PGD-20 accuracy: 70.51% vs 71.02%No clear effect
use WRN-34-10 instead of WRN-28-10 with decay at 150 (ablation)AGKD-BML-10 · CIFAR-10AutoAttack accuracy: 50.73% -> 51.63%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