AI Paper Atlas

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

Improving Adversarial Robustness via Activation Amplification and Attenuation

Taïga Gonçalves, Yongsong Huang, Tomo Miyazaki, Shinichiro Omachi

ECCV 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 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 A3 moduleAT ResNet-18 · CIFAR-10PGD-20 accuracy (%): 49.12 -> 58.66Improved
add A3 moduleAT ResNet-18 · CIFAR-10AutoAttack accuracy (%): 44.28 -> 47.28Improved
add A3 moduleAT ResNet-18 · CIFAR-10Clean accuracy (%): 85.04 -> 84.37Hurt
add A3 moduleAT WideResNet-34-10 · CIFAR-10AutoAttack accuracy (%): 48.18 -> 51.62Improved
use attenuation mode instead of amplification mode at inference (ablation)A3 · CIFAR-10 (AT, ResNet-18)AutoAttack accuracy (%): 45.92 -> 47.28Improved
use attenuation instead of hard suppression (ablation)A3 · CIFAR-10 (AT, ResNet-18)AutoAttack accuracy (%): 15.13 -> 47.28Improved
add contrastive logit loss L_cl (ablation)A3 · CIFAR-10 (AT, ResNet-18)AutoAttack accuracy (%): 46.70 -> 47.28Improved
add ranking loss L_rank (ablation)A3 · CIFAR-10 (AT, ResNet-18)PGD-20 accuracy (%): 51.41 -> 58.66Improved
use hinge ranking loss instead of unconstrained CE difference (ablation)A3 · CIFAR-10 (AT, ResNet-18)AutoAttack accuracy (%): 46.84 -> 47.28Improved
use log scaling instead of linear scaling (ablation)A3 · CIFAR-10 (AT, ResNet-18)PGD-20 accuracy (%): 51.95 -> 58.66Improved
use Gumbel-Softmax mask instead of hard-threshold mask (ablation)A3 · CIFAR-10 (AT, ResNet-18)PGD-20 accuracy (%): 52.23 -> 58.66Improved
insert A3 after block 4 instead of block 1 (ablation)A3 · CIFAR-10 (AT, ResNet-18)PGD-20 accuracy (%): 52.12 -> 58.66Improved

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