Enregistré dans:
Détails bibliographiques
Auteurs principaux: Piorkowski, David, Hind, Michael, Richards, John, Martino, Jacquelyn
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2506.02066
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916774411239424
author Piorkowski, David
Hind, Michael
Richards, John
Martino, Jacquelyn
author_facet Piorkowski, David
Hind, Michael
Richards, John
Martino, Jacquelyn
contents As foundation models grow in both popularity and capability, researchers have uncovered a variety of ways that the models can pose a risk to the model's owner, user, or others. Despite the efforts of measuring these risks via benchmarks and cataloging them in AI risk taxonomies, there is little guidance for practitioners on how to determine which risks are relevant for a given foundation model use. In this paper, we address this gap and develop requirements and an initial design for a risk identification framework. To do so, we look to prior literature to identify challenges for building a foundation model risk identification framework and adapt ideas from usage governance to synthesize four design requirements. We then demonstrate how a candidate framework can addresses these design requirements and provide a foundation model use example to show how the framework works in practice for a small subset of risks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02066
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Developing a Risk Identification Framework for Foundation Model Uses
Piorkowski, David
Hind, Michael
Richards, John
Martino, Jacquelyn
Cryptography and Security
As foundation models grow in both popularity and capability, researchers have uncovered a variety of ways that the models can pose a risk to the model's owner, user, or others. Despite the efforts of measuring these risks via benchmarks and cataloging them in AI risk taxonomies, there is little guidance for practitioners on how to determine which risks are relevant for a given foundation model use. In this paper, we address this gap and develop requirements and an initial design for a risk identification framework. To do so, we look to prior literature to identify challenges for building a foundation model risk identification framework and adapt ideas from usage governance to synthesize four design requirements. We then demonstrate how a candidate framework can addresses these design requirements and provide a foundation model use example to show how the framework works in practice for a small subset of risks.
title Developing a Risk Identification Framework for Foundation Model Uses
topic Cryptography and Security
url https://arxiv.org/abs/2506.02066