AI Paper Atlas

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

Robust Network Architecture Search via Feature Distortion Restraining

Yaguan Qian, Shenghui Huang, Bin Wang, Xiang Ling, Xiaohui Guan, Zhaoquan Gu, Shaoning Zeng, Wujie Zhou, Haijiang Wang

ECCV 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 6 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 network-vulnerability constraint (RNAS-H vs DARTS search)DARTS · CIFAR-10 (PGD AT)PGD20 robust accuracy (%): 44.91 -> 53.48Improved
add network-vulnerability constraint (RNAS-H vs DARTS search)DARTS · CIFAR-10 (PGD AT)AutoAttack robust accuracy (%): 39.98 -> 50.54Improved
tighten vulnerability bound from H=0.0001 to H=0.00001 (RNAS-L) (ablation)RNAS · CIFAR-10 (PGD AT)PGD20 robust accuracy (%): 53.48 -> 54.85Improved
tighten vulnerability bound from H=0.0001 to H=0.00001 (RNAS-L) (ablation)RNAS · CIFAR-100 (transferred)AutoAttack robust accuracy (%): 28.29 -> 27.37Hurt
tighten vulnerability bound from H=0.0001 to H=0.00001 (RNAS-L) (ablation)RNAS · SVHN (transferred)AutoAttack robust accuracy (%): 77.26 -> 75.89Hurt
tighten vulnerability bound from H=0.0001 to H=0.00001 (RNAS-L) (ablation)RNAS · Tiny-ImageNet (transferred)AutoAttack robust accuracy (%): 24.22 -> 23.02Hurt
tighten vulnerability bound from H=0.0001 to H=0.00001 (RNAS-L) (ablation)RNAS · Tiny-ImageNet (searched directly)AutoAttack robust accuracy (%): 24.82 -> 25.74Improved
decrease H (stronger constraint) toward very small values (ablation)RNAS · CIFAR-10/CIFAR-100/SVHN (Fig. 5)PGD20 robust accuracyMixed
search architecture directly on Tiny-ImageNet instead of transferring from CIFAR-10 (RNAS-L) (ablation)RNAS-L · Tiny-ImageNetAutoAttack robust accuracy (%): 23.02 -> 25.74Improved
use RNAS cell with only standard trainingRNAS-L · CIFAR-10 (standard training)FGSM accuracy (%): 54.72 -> 65.32Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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