AI Paper Atlas

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

Mitigating Error Amplification in Fast Adversarial Training

Mengnan Zhao, Lihe Zhang, Bo Wang, Tianhang Zheng, Hong Zhong, Geyong Min

CVPR 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training refinements · 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 perturbation budget allocation (PBA) (ablation)DDG · CIFAR-10 (best)clean accuracy: 81.70 -> 82.67Improved
add perturbation budget allocation (PBA) (ablation)DDG · CIFAR-10 (best)APGD accuracy: 57.46 -> 59.48Improved
add supervision signal adjustment (SSA) (ablation)DDG · CIFAR-10 (best)clean accuracy: 80.38 -> 82.67Improved
add supervision signal adjustment (SSA) (ablation)DDG · CIFAR-10 (best)C&W20 accuracy: 50.87 -> 49.86Hurt
add gradient smoothness regularization (GS) (ablation)DDG · CIFAR-10 (best)PGD-10 accuracy: 58.71 -> 60.44Improved
add gradient smoothness regularization (GS) (ablation)DDG · CIFAR-10 (best)clean accuracy: 84.32 -> 82.67Hurt
apply DDG instead of TDATResNet-18 FAT · CIFAR-10 (best)PGD-50 accuracy: 55.41 -> 59.33Improved
apply DDG instead of TDATResNet-18 FAT · CIFAR-100 (best)PGD-10 accuracy: 33.56 -> 34.42Improved
apply DDG instead of TDATResNet-18 FAT · Tiny-ImageNet (best)PGD-10 accuracy: 23.98 -> 24.35Improved
apply DDG instead of TDATResNet-18 FAT · CIFAR-10 (best)AutoAttack accuracy: 48.06 -> 48.08No clear effect
scale negative suppression term from 0 to 1.0 (ablation)y_sr · CIFAR-10clean accuracy: 81.50 -> 82.94Improved
scale negative suppression term from 0 to 1.0 (ablation)y_sr · CIFAR-10C&W10 accuracy: 51.02 -> 50.75Hurt

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