The term model robustness originates from the fields of Artificial Intelligence, Big Data and Smart Data, and cybercrime and cybersecurity. It describes how resilient an AI model or a data-based system is to disturbances, errors, or unknown data. A robust model therefore continues to function reliably even when confronted with new, unfamiliar, or faulty inputs.
Why is model robustness important? In practice, many AI applications – for example, in credit scoring or image recognition – often work with data that may contain small deviations, errors, or manipulations. A model that still makes the correct decisions in such situations is considered robust.
A vivid example: Imagine facial recognition software that can correctly identify people even when they are wearing glasses, poorly lit, or the photo is slightly blurred. Only a robust model can handle such minor disturbances and still deliver reliable results. Model robustness is therefore a crucial factor for the safety, fairness, and reliability of AI applications in the digital world.
Deutsch 
English (UK)