Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2310.16727 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916531491831808 |
|---|---|
| author | Schnitzer, Ronald Hapfelmeier, Andreas Gaube, Sven Zillner, Sonja |
| author_facet | Schnitzer, Ronald Hapfelmeier, Andreas Gaube, Sven Zillner, Sonja |
| contents | Recent advancements in the field of Artificial Intelligence (AI) establish the basis to address challenging tasks. However, with the integration of AI, new risks arise. Therefore, to benefit from its advantages, it is essential to adequately handle the risks associated with AI. Existing risk management processes in related fields, such as software systems, need to sufficiently consider the specifics of AI. A key challenge is to systematically and transparently identify and address AI risks' root causes - also called AI hazards. This paper introduces the AI Hazard Management (AIHM) framework, which provides a structured process to systematically identify, assess, and treat AI hazards. The proposed process is conducted in parallel with the development to ensure that any AI hazard is captured at the earliest possible stage of the AI system's life cycle. In addition, to ensure the AI system's auditability, the proposed framework systematically documents evidence that the potential impact of identified AI hazards could be reduced to a tolerable level. The framework builds upon an AI hazard list from a comprehensive state-of-the-art analysis. Also, we provide a taxonomy that supports the optimal treatment of the identified AI hazards. Additionally, we illustrate how the AIHM framework can increase the overall quality of a power grid AI use case by systematically reducing the impact of identified hazards to an acceptable level. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_16727 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | AI Hazard Management: A framework for the systematic management of root causes for AI risks Schnitzer, Ronald Hapfelmeier, Andreas Gaube, Sven Zillner, Sonja Machine Learning Recent advancements in the field of Artificial Intelligence (AI) establish the basis to address challenging tasks. However, with the integration of AI, new risks arise. Therefore, to benefit from its advantages, it is essential to adequately handle the risks associated with AI. Existing risk management processes in related fields, such as software systems, need to sufficiently consider the specifics of AI. A key challenge is to systematically and transparently identify and address AI risks' root causes - also called AI hazards. This paper introduces the AI Hazard Management (AIHM) framework, which provides a structured process to systematically identify, assess, and treat AI hazards. The proposed process is conducted in parallel with the development to ensure that any AI hazard is captured at the earliest possible stage of the AI system's life cycle. In addition, to ensure the AI system's auditability, the proposed framework systematically documents evidence that the potential impact of identified AI hazards could be reduced to a tolerable level. The framework builds upon an AI hazard list from a comprehensive state-of-the-art analysis. Also, we provide a taxonomy that supports the optimal treatment of the identified AI hazards. Additionally, we illustrate how the AIHM framework can increase the overall quality of a power grid AI use case by systematically reducing the impact of identified hazards to an acceptable level. |
| title | AI Hazard Management: A framework for the systematic management of root causes for AI risks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2310.16727 |