research
∙
08/03/2023
Assessing Systematic Weaknesses of DNNs using Counterfactuals
With the advancement of DNNs into safety-critical applications, testing ...
share
research
∙
08/02/2023
Using ScrutinAI for Visual Inspection of DNN Performance in a Medical Use Case
Our Visual Analytics (VA) tool ScrutinAI supports human analysts to inve...
research
∙
06/20/2023
Guideline for Trustworthy Artificial Intelligence – AI Assessment Catalog
Artificial Intelligence (AI) has made impressive progress in recent year...
research
∙
04/22/2021
Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities
An important pillar for safe machine learning (ML) is the systematic mit...
research
∙
11/28/2019
Communication-Efficient Distributed Online Learning with Kernels
We propose an efficient distributed online learning protocol for low-lat...
research
∙
11/28/2019