Conference Paper · 2026
Towards a Domain-Agnostic Safety-by-Design AI Engineering Pipeline
Advanced Information Systems Engineering Workshops (CAiSE Workshops)
The Short Version
The Safe AI Pipeline connects data, model, and monitoring design in an iterative Safety-by-Design workflow, demonstrated with an MNIST proof of concept.
Abstract
AI-based applications already revolutionize our everyday lives; however, it remains unclear how to assess their safety given their black-box nature. Certifying them for safety-critical applications is thus still under current research. Therefore, we developed the Safe AI Pipeline (SAIPi) as an example of a safety-by-design approach to the engineering of AI systems. The pipeline contains several tools for data, model, and monitoring design, fulfilling requirements such as data completeness and model accuracy. We use MNIST as an exemplary showcase and proof of concept for developing deep learning models. We completed an entire iteration of the pipeline, which demonstrates how to engineer an AI system in a safe, iterative way. Future work will improve the tool and pipeline and increase the complexity of use cases.
Reference
Cite This Work
Elena Hoemann, Akshay Anilkumar Girija, Johann Maximilian Christensen, Yannick Kees, Florian Krone, Thomas Liebert, Ryan Mut, Gerald Sauter, Thomas Stefani, Frank Köster, Sven Hallerbach. "Towards a Domain-Agnostic Safety-by-Design AI Engineering Pipeline". Advanced Information Systems Engineering Workshops (CAiSE Workshops), 2026.