AI Paper Atlas

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

FERD: Fairness-Enhanced Data-Free Adversarial Robustness Distillation

Zhengxiao Li, Liming Lu, Xu Zheng, Si Yuan Liang, Taric Chen, Yongbin Zhou, Shuchao Pang

ICLR 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Theory of adversarial risk

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 robustness-guided class reweighting (ablation)FERD · CIFAR-10 (WRN-34-10 teacher) ResNet-18 AutoAttackworst-class robustness: 17.20 -> 20.80Improved
add robustness-guided class reweighting (ablation)FERD · CIFAR-10 (WRN-34-10 teacher) ResNet-18 cleanworst-class accuracy: 63.20 -> 65.90Improved
add robustness-guided class reweighting (ablation)FERD · CIFAR-10 (WRN-34-10 teacher) ResNet-18 cleanaverage accuracy: 79.53 -> 79.26Hurt
add FAEs (ablation)FERD · CIFAR-10 (WRN-34-10 teacher) ResNet-18 AutoAttackworst-class robustness: 19.90 -> 20.80Improved
add UTAEs (ablation)FERD · CIFAR-10 (WRN-34-10 teacher) ResNet-18 AutoAttackworst-class robustness: 20.00 -> 20.80Improved
add both FAEs and UTAEs (ablation)FERD · CIFAR-10 (WRN-34-10 teacher) ResNet-18 AutoAttackaverage robustness: 40.92 -> 42.24Improved
add both FAEs and UTAEs (ablation)FERD · CIFAR-10 (WRN-34-10 teacher) ResNet-18 cleanworst-class accuracy: 62.50 -> 65.90Improved
use FERD reweighting instead of power-type reweighting (ablation)FERD reweighting on CIFAR-10 ResNet-18 · CIFAR-10 (WRN-34-10 teacher) ResNet-18 PGDworst-class robustness: 17.90 -> 20.40Improved
use FERD reweighting instead of linear reweighting (ablation)FERD reweighting on CIFAR-10 ResNet-18 · CIFAR-10 (WRN-34-10 teacher) ResNet-18 FGSMworst-class robustness: 29.10 -> 31.30Improved
use FERD reweighting instead of sigmoid or tanh reweighting (ablation)FERD reweighting on CIFAR-10 ResNet-18 · CIFAR-10 (WRN-34-10 teacher) ResNet-18 cleanaverage accuracy: 80.16 -> 79.26Hurt
use penultimate residual module (block3) for non-robust feature distillation instead of block1 (ablation)FERD · CIFAR-10 (WRN-34-10 teacher) ResNet-18 PGD-20worst-class robustness: 20.00 -> 23.50Improved
raise lambda_bn and lambda_uni from 1 to 5 (ablation)FERD generator loss · CIFAR-10 (WRN-34-10 teacher) ResNet-18 AutoAttackworst-class robustness: 16.90 -> 20.80Improved

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