Julian Bitterwolf

Maximilian Müller

Proceedings of the International Conference on Machine Learning, 2023

2022

Neural Network Heuristic Functions: Taking Confidence into Account.

[BibT_eX]

[DOI]

Proceedings of the Fifteenth International Symposium on Combinatorial Search, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

2021

Provably Robust Detection of Out-of-distribution Data (almost) for free.

[BibT_eX]

[DOI]

CoRR, 2021

2020

Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data.

[BibT_eX]

[DOI]

CoRR, 2020

Increasing the robustness of DNNs against image corruptions by playing the Game of Noise.

[BibT_eX]

[DOI]

CoRR, 2020

Certifiably Adversarially Robust Detection of Out-of-Distribution Data.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

2019

Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem.

[BibT_eX]

[DOI]

Maksym Andriushchenko