AI Paper Atlas

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

Adversarial Robustness on In- and Out-Distribution Improves Explainability

Maximilian Augustin, Alexander Meinke, Matthias Hein

ECCV 2020 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 62 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 adversarial training on the out-distribution (ACET) to AT0.5 (RATIO-0.5) (ablation)AT0.5 · CIFAR10robust accuracy l2 eps=0.5 (%): 70.42 -> 73.27Improved
add adversarial training on the out-distribution to AT0.5 (RATIO-0.5) (ablation)AT0.5 · CIFAR10worst-case OOD AUC l2 eps=1.0 (%): 57.4 -> 83.6Improved
add adversarial training on the out-distribution to AT0.25 (RATIO-0.25) (ablation)AT0.25 · CIFAR10worst-case OOD AUC l2 eps=1.0 (%): 42.0 -> 84.3Improved
add adversarial training on the out-distribution to AT0.25 (RATIO-0.25) (ablation)AT0.25 · CIFAR10clean accuracy (%): 94.00 -> 93.53No clear effect
add adversarial training on the in-distribution to ACET (RATIO-0.25) (ablation)ACET · CIFAR10worst-case OOD AUC l2 eps=1.0 (%): 81.9 -> 84.3Improved
add adversarial training on the out-distribution to AT0.5 (RATIO-0.5) (ablation)AT0.5 · SVHNrobust accuracy l2 eps=0.5 (%): 68.58 -> 68.85No clear effect
add adversarial training on the out-distribution to AT0.5 (RATIO-0.5) (ablation)AT0.5 · CIFAR100robust accuracy l2 eps=0.5 (%): 43.23 -> 45.55Improved
add adversarial training on the out-distribution to AT3.5 (RATIO-3.5) (ablation)AT3.5 · Restricted ImageNetworst-case OOD AUC l2 eps=7.0 (%): 37.5 -> 90.9Improved
use smaller in-distribution radius 0.25 instead of 0.5 for RATIO (ablation)RATIO · CIFAR10clean accuracy (%): 91.08 -> 93.53Improved
use smaller in-distribution radius 0.25 instead of 0.5 for RATIO (ablation)RATIO · CIFAR10robust accuracy l2 eps=0.5 (%): 73.27 -> 70.49Hurt
add out-distribution training and adversarial training (RATIO) instead of TRADES trainingTRADES (own implementation) · CIFAR10robust accuracy l2 eps=0.5 (%): 71.02 -> 73.27Improved
train with outlier exposure only (OE) instead of plain training (ablation)Plain · CIFAR10worst-case OOD AUC l2 eps=1.0 (%): 1.6 -> 8.7No clear effect

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