Asja Fischer
Institution: Ruhr-Universität Bochum / CASA
Research Hub(s):
Hub C: Sichere Systeme
E-Mail: Asja.Fischer@rub.de
Adresse: IB 3/153
Website: https://informatik.rub.de/ml/
Publikationen:
Infinite ensembles for uncertainty prediction (Workshop-Beitrag) Efficient Calculation of Adversarial Examples for Bayesian Neural Networks Approaches to Uncertainty Quantification in Federated Deep Learning SmoothLRP: Smoothing LRP by Averaging over Stochastic Input Variations How Sampling Impacts the Robustness of Stochastic Neural Networks Towards the Detection of Diffusion Model Deepfakes Detecting Compositionally Out-of-Distribution Examples in Semantic Parsing Uncertainty quantification with compound density network (Workshop-Beitrag) Leveraging Frequency Analysis for Deep Fake Image Recognition Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification