AI Paper Atlas

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

Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks

Louis Béthune, Paul Novello, Guillaume Coiffier, Thibaut Boissin, Mathieu Serrurier, Quentin VINCENOT, Andres Troya-Galvis

ICML 2023 · Adversarial robustness and security › Certified and empirical robustness · approach: Neural network robustness verification · 2 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
Use OCSDF instead of Deep SVDDMNIST one-versus-all · MNIST one-versus-allmAUROC: 95.5\pm 0.4 vs 94.8\pm 0.9No clear effect
Use OCSDF instead of the strongest reported conventional baselineCIFAR10 one-versus-all · CIFAR10 one-versus-allmAUROC: 57.4\pm 2.1 vs 64.8\pm 8.0Hurt
Use OCSDF for Cats-versus-Dogs detectionOCSDF · Cats versus Dogs (Cats normal)AUROC: 55.0\%Hurt
Increase the certified l2 attack radiusOCSDF on MNIST · MNIST one-versus-allcertified mAUROC: 95.5\pm 0.4 -> 57.5\pm 7.5Hurt
Increase the certified l2 attack radiusOCSDF on CIFAR10 · CIFAR10 one-versus-allcertified mAUROC: 57.4\pm 2.1 -> 22.5\pm 1.4Hurt
Tune the margin separately for each CIFAR-10 class (ablation)OCSDF on CIFAR10 · CIFAR10 one-versus-allAUROCImproved

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