The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis
This addresses the challenge of certifying safe AI for regulatory compliance, but it is incremental as it analyzes existing XAI methods without proposing new solutions.
The study examined the potential of eXplainable AI (XAI) methods for safe AI development and certification through 15 expert interviews, finding that XAI can help identify biases and failures in ML models but has limited impact due to certification's need for comprehensive and correct information.
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 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. We find that XAI methods can be a helpful asset for safe AI development, as they can show biases and failures of ML-models, but since certification relies on comprehensive and correct information about technical systems, their impact is expected to be limited.