Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection

Nicola Franco, Daniel Korth, Jeanette Miriam Lorenz, Karsten Roscher, Stephan Günnemann

Research output: Contribution to journalConference articlepeer-review


As the use of machine learning continues to expand, the importance of ensuring its safety cannot be overstated. A key concern in this regard is the ability to identify whether a given sample is from the training distribution, or is an "Out-Of-Distribution" (OOD) sample. In addition, adversaries can manipulate OOD samples in ways that lead a classifier to make a confident prediction. In this study, we present a novel approach for certifying the robustness of OOD detection within a ℓ2-norm around the input, regardless of network architecture and without the need for specific components or additional training. Further, we improve current techniques for detecting adversarial attacks on OOD samples, while providing high levels of certified and adversarial robustness on in-distribution samples. The average of all OOD detection metrics on CIFAR10/100 shows an increase of-13%/5% relative to previous approaches. Code: https://github.com/FraunhoferIKS/distro

Original languageEnglish
JournalCEUR Workshop Proceedings
StatePublished - 2023
Event2023 IJCAI Joint Workshop on Artificial Intelligence Safety and Safe Reinforcement Learning, AISafety-SafeRL 2023 - Macau, China
Duration: 21 Aug 202322 Aug 2023


  • Out-Of-Distribution
  • Randomized Smoothing
  • Robust Machine Learning
  • Robustness Certificates


Dive into the research topics of 'Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection'. Together they form a unique fingerprint.

Cite this