AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Certifiably Adversarially Robust Detection of Out-of-Distribution Data

Julian Bitterwolf, Alexander Meinke, Matthias Hein

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Probabilistic calibration · 16 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 IBP-based worst-case confidence bound loss on OOD inputs (GOOD100 vs OE)OOD detection training · MNIST FashionMNISTguaranteed AUC (GAUC): 0.0 -> 78.0Improved
GOOD100 vs ACET on empirical adversarial AUCOOD detection training · MNIST FashionMNISTadversarial AUC (AAUC): 98.4 -> 96.5Hurt
use GOOD100 instead of plain trainingMNIST classifier · MNISTtest accuracy: 99.4 -> 98.7Hurt
use GOOD100 instead of OESVHN classifier · SVHNtest accuracy: 95.5 -> 96.3Improved
use GOOD80 instead of OECIFAR-10 classifier · CIFAR-10test accuracy: 90.7 -> 90.1No clear effect
apply worst-case loss to all OOD samples (quantile 100) instead of 80 on CIFAR-10 (ablation)GOOD · CIFAR-10 vs CIFAR-100clean AUC: 85.6 -> 70.0Hurt
apply worst-case loss to all OOD samples (quantile 100) instead of 80 on CIFAR-10 (ablation)GOOD · CIFAR-10 vs CIFAR-100guaranteed AUC (GAUC): 42.3 -> 54.2Improved
add quantile restriction (GOOD80) instead of GOOD100 for the difficult CIFAR-10 task (ablation)GOOD · CIFAR-10 vs CIFAR-100clean AUC: 70.0 -> 85.6Improved
add worst-case term for part of OOD samples (GOOD60 vs GOOD0) (ablation)GOOD · CIFAR-10 vs CIFAR-100guaranteed AUC (GAUC): 0.0 -> 34.9Improved
GOOD100 vs OE on EMNIST letters detectionMNIST classifier · EMNIST LettersAUC: 92.7 -> 99.0Improved
GOOD80 vs ACET on empirical AAUC on CIFAR-10CIFAR-10 OOD detection · CIFAR-10 vs CIFAR-100adversarial AUC (AAUC): 74.5 -> 48.2Hurt

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