On the (In)Security of Loading Machine Learning Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Digregorio, Gabriele, Di Gennaro, Marco, Zanero, Stefano, Longari, Stefano, Carminati, Michele
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911510575448064
author Digregorio, Gabriele
Di Gennaro, Marco
Zanero, Stefano
Longari, Stefano
Carminati, Michele
author_facet Digregorio, Gabriele
Di Gennaro, Marco
Zanero, Stefano
Longari, Stefano
Carminati, Michele
contents The rise of model sharing through frameworks and dedicated hubs makes Machine Learning significantly more accessible. Despite its benefits, loading shared models exposes users to underexplored security risks, while security awareness remains limited among both practitioners and developers. To enable a more security-conscious approach in Machine Learning model sharing, in this paper, we evaluate the security posture of frameworks and hubs, assess whether security-oriented mechanisms offer real protection, and survey how users perceive the security narratives surrounding model sharing. Our evaluation shows that most frameworks and hubs address security risks partially at best, often by shifting responsibility to the user. More concerningly, our analysis of frameworks advertising security-oriented settings and complete model sharing uncovered multiple 0-day vulnerabilities enabling arbitrary code execution. Through this analysis, we show that, despite the recent narrative, securely loading Machine Learning models is far from being a solved problem and cannot be guaranteed by the file format used for sharing. Our survey shows that the security narrative leads users to consider security-oriented settings as trustworthy, despite the weaknesses shown in this work. From this, we derive suggestions to strengthen the security of model-sharing ecosystems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06703
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the (In)Security of Loading Machine Learning Models
Digregorio, Gabriele
Di Gennaro, Marco
Zanero, Stefano
Longari, Stefano
Carminati, Michele
Cryptography and Security
Machine Learning
The rise of model sharing through frameworks and dedicated hubs makes Machine Learning significantly more accessible. Despite its benefits, loading shared models exposes users to underexplored security risks, while security awareness remains limited among both practitioners and developers. To enable a more security-conscious approach in Machine Learning model sharing, in this paper, we evaluate the security posture of frameworks and hubs, assess whether security-oriented mechanisms offer real protection, and survey how users perceive the security narratives surrounding model sharing. Our evaluation shows that most frameworks and hubs address security risks partially at best, often by shifting responsibility to the user. More concerningly, our analysis of frameworks advertising security-oriented settings and complete model sharing uncovered multiple 0-day vulnerabilities enabling arbitrary code execution. Through this analysis, we show that, despite the recent narrative, securely loading Machine Learning models is far from being a solved problem and cannot be guaranteed by the file format used for sharing. Our survey shows that the security narrative leads users to consider security-oriented settings as trustworthy, despite the weaknesses shown in this work. From this, we derive suggestions to strengthen the security of model-sharing ecosystems.
title On the (In)Security of Loading Machine Learning Models
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2509.06703