Research Issues and Challenges in the Computational Development of Trustworthy AI
Shahina Begum, Mobyen Uddin Ahmed, Shaibal Barua, Md Alamgir Kabir, Abu Naser Masud · 2024
The development and deployment of AI systems necessitate a steadfast commitment to reliability, safety, security, ethics, and social responsibility. This paper introduces key research issues and challenges for trustworthy AI based on our experience working on several ongoing research projects at Mälardalen University (MDU), Sweden, which considers practical, real-world scenarios from the mobility, transportation, and healthcare domains. Our observations have highlighted several critical technical components that underpin trustworthy AI. These components include fairness, safety, transparency, explainability, accountability, rigorous testing, verification, and a human-centric approach to AI. Notably, these elements align closely with the current state-of-the-art practices in the field.