The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis

Developing and certifying safe—or so-called trustworthy—AI has become an increasingly salient issue, especially in light of recently introduced regulation such as the EU AI Act. In this context, the black-box nature of machine learning models limits the use of conventional avenues of approach towards certifying complex technical systems. As a potential solution, methods to give insights into this black-box—devised in the field of eXplainable AI (XAI)—could be used. In this study, the potential and shortcomings of such methods for the purpose of safe AI development and certification are discussed in 15 qualitative interviews with experts out of the areas of (X)AI and certification. The interview results are summarized as a set of recommendations for policy makers and XAI researchers and developers. Overall, XAI methods are found to be a helpful asset for safe AI development, as they can show biases and failures of machine learning models, but since certification relies on comprehensive and correct information about technical systems, their impact is expected to be limited.