Explainability Requirements in Software-Intensive Systems
| Typ | Masterarbeit | |
|---|---|---|
| Aushang | ||
| Betreuer | Wenden Sie sich bei Interesse oder Fragen bitte an: Raffaela Mirandola (E-Mail: raffaela.mirandola@kit.edu) |
Motivation
Software-intensive systems range from enterprise systems to IoTs and cyber-physical systems to industrial control systems where software plays a vital role. In such systems, decision-making is software-supported in an automated and/or autonomous way.
However, trust can be hindered by the black-box nature of these systems, whose autonomous decisions may be confusing or even dangerous for humans. Thus, explainability emerges as a crucial non-functional property to be featured to achieve transparency and increase awareness of the systems' behaviour, hopefully leading to their acceptance in our society.
Tasks
The thesis aims to explore the treatment of explainability as a non-functional system requirement.
The main tasks will be:
- Definition of a framework that characterises the explainability requirements in terms of phenomena to be explained, context, and recipient stakeholders of the explanation.
- Definition of a quantitative measure for explainability
- Evaluation of trade-off between explainability and dependability
Benefits
- Insight into a highly relevant field of research
- Opportunity to develop innovative technologies
- Close connection to a current research project
- Very good working environment and intensive support