AI Paper Atlas

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

Provably Adversarially Robust Detection of Out-of-Distribution Data (Almost) for Free

Alexander Meinke, Julian Bitterwolf, Matthias Hein

NeurIPS 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 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 certified binary discriminator to OE classifier (ProoD vs OE)OE ResNet18 · CIFAR10 vs SVHNAAUC: 0.0 -> 54.1Improved
add certified binary discriminator to OE classifier (ProoD vs OE)OE ResNet18 · CIFAR10 testaccuracy: 94.91 -> 94.99No clear effect
ProoD vs GOOD80 (architecture-unconstrained classifier)GOOD80 · CIFAR10 testaccuracy: 87.39 -> 94.99Improved
ProoD vs GOOD80 on guaranteed AUCGOOD80 · CIFAR10 vs CIFAR100GAUC: 47.1 -> 46.1Hurt
ProoD vs GOOD80 on guaranteed AUCGOOD80 · CIFAR10 vs SVHNGAUC: 43.4 -> 53.3Improved
ProoD vs adversarially trained ATOMATOM · CIFAR10 vs SVHNAAUC: 24.1 -> 54.1Improved
ProoD vs ATOM on CIFAR100ATOM · CIFAR100 vs CIFAR10AAUC: 50.3 -> 17.4Hurt
ProoD vs ATOM on accuracy CIFAR100ATOM · CIFAR100 testaccuracy: 68.32 -> 77.16Improved
add classifier to discriminator (ProoD-Disc to ProoD) for clean OOD detection (ablation)ProoD-Disc · CIFAR10 vs CIFAR100AUC: 62.9 -> 89.8Improved
semi-joint training of classifier through the fixed discriminator instead of separate training (ablation)ProoD · CIFAR10guaranteed AUCImproved
positive bias shift Delta on discriminator output (sweep 0 to 6) (ablation)ProoD · CIFAR10/CIFAR100/R.ImgNetAUC vs guaranteed AUC trade-offMixed
enforce negative output-layer weights of discriminator (ablation)ProoD · CIFAR10 testaccuracy and OOD AUCNo 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