Sina Däubener

Ruhr-Universität Bochum

H-index: 6

Europe-Germany

Sina Däubener, With an exceptional h-index of 6 and a recent h-index of 6 (since 2020), a distinguished researcher at Ruhr-Universität Bochum,

His recent articles reflect a diverse array of research interests and contributions to the field:

On the Limitations of Model Stealing with Uncertainty Quantification Models

Approaches to uncertainty quantification in federated deep learning

How Sampling Impacts the Robustness of Stochastic Neural Networks

Detecting Compositionally Out-of-Distribution Examples in Semantic Parsing

SmoothLRP: Smoothing LRP by Averaging over Stochastic Input Variations.

Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification

Investigating maximum likelihood based training of infinite mixtures for uncertainty quantification

Title	Journal	Author(s)	Publication Date
On the Limitations of Model Stealing with Uncertainty Quantification Models	European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)	David Pape Sina Däubener Thorsten Eisenhofer Antonio Emanuele Cinà Lea Schönherr	2023
Approaches to uncertainty quantification in federated deep learning		Florian Linsner Linara Adilova Sina Däubener Michael Kamp Asja Fischer	2022/2/17
How Sampling Impacts the Robustness of Stochastic Neural Networks	arXiv preprint arXiv:2204.10839	Sina Däubener Asja Fischer	2022/4/22
Detecting Compositionally Out-of-Distribution Examples in Semantic Parsing		Denis Lukovnikov Sina Daubener Asja Fischer	2021/11
SmoothLRP: Smoothing LRP by Averaging over Stochastic Input Variations.		Arne P Raulf Sina Däubener Ben Hack Axel Mosig Asja Fischer	2021
Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification	arXiv preprint arXiv:2005.14611	Sina Däubener Lea Schönherr Asja Fischer Dorothea Kolossa	2020/5/24
Investigating maximum likelihood based training of infinite mixtures for uncertainty quantification	arXiv preprint arXiv:2008.03209	Sina Däubener Asja Fischer	2020/8/7

Useful Links