Papers › Certifiably Adversarially Robust Detection of Out-of-Distribution Data

Certifiably Adversarially Robust Detection of Out-of-Distribution Data

16 Jul 2020NeurIPS 2020 12arXiv:2007.08473archive 2025-07-28

Julian Bitterwolf, Alexander Meinke, Matthias Hein

Deep neural networks are known to be overconfident when applied to out-of-distribution (OOD) inputs which clearly do not belong to any class. This is a problem in safety-critical applications since a reliable assessment of the uncertainty of a classifier is a key property, allowing the system to trigger human intervention or to transfer into a safe state. In this paper, we aim for certifiable worst case guarantees for OOD detection by enforcing not only low confidence at the OOD point but also in an l_∞-ball around it. For this purpose, we use interval bound propagation (IBP) to upper bound the maximal confidence in the l_∞-ball and minimize this upper bound during training time. We show that non-trivial bounds on the confidence for OOD data generalizing beyond the OOD dataset seen at training time are possible. Moreover, in contrast to certified adversarial robustness which typically comes with significant loss in prediction performance, certified guarantees for worst case OOD detection are possible without much loss in accuracy.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

gitlab.com/Bitterwolf/GOOD officialmentioned in papermentioned on GitHubpytorch report
j-cb/GOOD mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Adversarial RobustnessOut of Distribution (OOD) Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections