Position: A taxonomy for reporting and describing AI security incidents

AI systems are vulnerable to attacks, and corresponding AI security incidents have been described. Although a collection of safety incidents around AI will become a regulatory requirement, there is no proposal to collect AI security incidents. In this position paper, we argue that a proposal should...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bieringer, Lukas, Paeth, Kevin, Wespi, Andreas, Grosse, Kathrin
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:AI systems are vulnerable to attacks, and corresponding AI security incidents have been described. Although a collection of safety incidents around AI will become a regulatory requirement, there is no proposal to collect AI security incidents. In this position paper, we argue that a proposal should be made, taking into account the interests and needs of different stakeholders: industry, providers, users, and researchers. We thus attempt to close this gap and propose a taxonomy alongside its requirements like machine readability and link-ability with existing databases. We aim to spark discussions and enable discussion of which information is feasible, necessary, and possible to report and share within and outside organizations using AI.
DOI:10.48550/arxiv.2412.14855