Security practices in AI development

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Spelda, Petr, Stritecky, Vit
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912505948798976
author Spelda, Petr
Stritecky, Vit
author_facet Spelda, Petr
Stritecky, Vit
contents What makes safety claims about general purpose AI systems such as large language models trustworthy? We show that rather than the capabilities of security tools such as alignment and red teaming procedures, it is security practices based on these tools that contributed to reconfiguring the image of AI safety and made the claims acceptable. After showing what causes the gap between the capabilities of security tools and the desired safety guarantees, we critically investigate how AI security practices attempt to fill the gap and identify several shortcomings in diversity and participation. We found that these security practices are part of securitization processes aiming to support (commercial) development of general purpose AI systems whose trustworthiness can only be imperfectly tested instead of guaranteed. We conclude by offering several improvements to the current AI security practices.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21061
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Security practices in AI development
Spelda, Petr
Stritecky, Vit
Cryptography and Security
Computers and Society
What makes safety claims about general purpose AI systems such as large language models trustworthy? We show that rather than the capabilities of security tools such as alignment and red teaming procedures, it is security practices based on these tools that contributed to reconfiguring the image of AI safety and made the claims acceptable. After showing what causes the gap between the capabilities of security tools and the desired safety guarantees, we critically investigate how AI security practices attempt to fill the gap and identify several shortcomings in diversity and participation. We found that these security practices are part of securitization processes aiming to support (commercial) development of general purpose AI systems whose trustworthiness can only be imperfectly tested instead of guaranteed. We conclude by offering several improvements to the current AI security practices.
title Security practices in AI development
topic Cryptography and Security
Computers and Society
url https://arxiv.org/abs/2507.21061