16 citations · 32 across the 7 of their papers we have counts for
3 papers · 1 filter
The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis
Benjamin Fresz, Vincent Philipp Göbels, Safa Omri +5
Developing and certifying safe - or so-called trustworthy - AI has become an increasingly salient issue, especially in light of upcoming regulation such as the EU AI Act. In this c…
Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations
Benjamin Fresz, Lena Lörcher, Marco Huber
Decision processes of computer vision models - especially deep neural networks - are opaque in nature, meaning that these decisions cannot be understood by humans. Thus, over the l…
How should AI decisions be explained? Requirements for Explanations from the Perspective of European Law
Benjamin Fresz, Elena Dubovitskaya, Danilo Brajovic +2
This paper investigates the relationship between law and eXplainable Artificial Intelligence (XAI). While there is much discussion about the AI Act, for which the trilogue of the E…