Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2511.11275 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908659013910528 |
|---|---|
| author | Wenzel, Julius Alam, Syeda Umaima Schmidt, Andreas Zhang, Hanwei Hermanns, Holger |
| author_facet | Wenzel, Julius Alam, Syeda Umaima Schmidt, Andreas Zhang, Hanwei Hermanns, Holger |
| contents | An ever increasing number of high-stake decisions are made or assisted by automated systems employing brittle artificial intelligence technology. There is a substantial risk that some of these decision induce harm to people, by infringing their well-being or their fundamental human rights. The state-of-the-art in AI systems makes little effort with respect to appropriate documentation of the decision process. This obstructs the ability to trace what went into a decision, which in turn is a prerequisite to any attempt of reconstructing a responsibility chain. Specifically, such traceability is linked to a documentation that will stand up in court when determining the cause of some AI-based decision that inadvertently or intentionally violates the law.
This paper takes a radical, yet practical, approach to this problem, by enforcing the documentation of each and every component that goes into the training or inference of an automated decision. As such, it presents the first running workflow supporting the generation of tamper-proof, verifiable and exhaustive traces of AI decisions. In doing so, we expand the DBOM concept into an effective running workflow leveraging confidential computing technology. We demonstrate the inner workings of the workflow in the development of an app to tell poisonous and edible mushrooms apart, meant as a playful example of high-stake decision support. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11275 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Workflow for Full Traceability of AI Decisions Wenzel, Julius Alam, Syeda Umaima Schmidt, Andreas Zhang, Hanwei Hermanns, Holger Artificial Intelligence An ever increasing number of high-stake decisions are made or assisted by automated systems employing brittle artificial intelligence technology. There is a substantial risk that some of these decision induce harm to people, by infringing their well-being or their fundamental human rights. The state-of-the-art in AI systems makes little effort with respect to appropriate documentation of the decision process. This obstructs the ability to trace what went into a decision, which in turn is a prerequisite to any attempt of reconstructing a responsibility chain. Specifically, such traceability is linked to a documentation that will stand up in court when determining the cause of some AI-based decision that inadvertently or intentionally violates the law. This paper takes a radical, yet practical, approach to this problem, by enforcing the documentation of each and every component that goes into the training or inference of an automated decision. As such, it presents the first running workflow supporting the generation of tamper-proof, verifiable and exhaustive traces of AI decisions. In doing so, we expand the DBOM concept into an effective running workflow leveraging confidential computing technology. We demonstrate the inner workings of the workflow in the development of an app to tell poisonous and edible mushrooms apart, meant as a playful example of high-stake decision support. |
| title | A Workflow for Full Traceability of AI Decisions |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2511.11275 |